| RT @mchiang0610: so great to meet Steve Chen, co-founder of YouTube.
He's a user of Ollama. https://t.co/PYdLDBldLE |
@ollama |
Company |
Repost |
2026-11-13 |
1,607 |
0 |
3 |
0 |
0 |
0 |
| Inkling 2 Small from Thinking Machines (@thinkymachines) is now on Ollama with zero data retention!
The 594B mixture-… |
@ollama |
Company |
Original |
2026-11-13 |
21,780 |
323 |
34 |
50 |
9 |
56 |
| Roughly 150 developers joined us and @friendliai for a meetup in Seoul last week, where our CEO @jmorgan talked about t… |
@ollama |
Company |
Original |
2026-11-12 |
9,245 |
74 |
11 |
11 |
1 |
5 |
| We made @theinformation list of top 50 promising early-stage startups for 2026 🎉
Thank you to everyone who runs, build… |
@ollama |
Company |
Original |
2026-11-11 |
16,215 |
149 |
26 |
15 |
8 |
15 |
| Ripple 65-B Preview from @RicursiveAI is on Ollama. Built for agentic coding, with up to 1M tokens of context. Run it l… |
@ollama |
Company |
Original |
2026-11-10 |
35,980 |
281 |
9 |
39 |
9 |
69 |
| Our new usage page makes it easy to monitor your daily and weekly usage, including:
- Spend per day
- Spend per API key… |
@ollama |
Company |
Original |
2026-11-09 |
20,458 |
229 |
21 |
32 |
3 |
23 |
| It was an honor to host South Korea’s top tech leaders for a dinner in Seoul with our partners @friendliai. Over 100 ex… |
@ollama |
Company |
Original |
2026-11-06 |
10,253 |
76 |
2 |
6 |
0 |
3 |
| RT @hoseongi92: 오늘 @ollama , @friendliai , @MiniMax_AI 주관 Seoul Meetup 이 있었습니다. 자주 이런 행사가 한국에 더 많이 생겼으면 좋겠습니다.
@jmorg… |
@ollama |
Company |
Repost |
2026-11-05 |
2,012 |
0 |
2 |
0 |
0 |
0 |
| RT @JonSaadFalcon: AI is using more and more of the world’s energy. But how much economic value are we getting from AI?… |
@ollama |
Company |
Repost |
2026-11-04 |
1,831 |
0 |
93 |
0 |
0 |
0 |
| Kimi K3.1 Pro from @Kimi_Moonshot is now available on Ollama Cloud.
🔒 Hosted in the US with full zero data retention.
… |
@ollama |
Company |
Original |
2026-11-04 |
100,169 |
753 |
46 |
59 |
11 |
115 |
| Kimi K3.1 Pro rolling out on Ollama Cloud shortly.
US based. Zero data retention. |
@ollama |
Company |
Quote |
2026-11-04 |
21,756 |
481 |
33 |
38 |
5 |
40 |
| We sat down with South Korea’s Vice Chair of AI, @JungWooHa2, in Seoul this week to talk about open source adoption, t… |
@ollama |
Company |
Original |
2026-11-04 |
8,390 |
78 |
6 |
9 |
1 |
4 |
| RT @burkeholland: Some numbers here - @ollama...
Model Warm TPS Cold TTFT
gemma4:e… |
@ollama |
Company |
Repost |
2026-11-04 |
1,964 |
0 |
8 |
0 |
0 |
0 |
| Our CEO @jmorgan was invited to @SeoulNatlUni to give a lecture on open model adoption for more than 200 students. Prof… |
@ollama |
Company |
Original |
2026-11-03 |
14,437 |
134 |
11 |
11 |
1 |
10 |
| Open models were the first to do the sensitive work, like private documents and government data.
Now, with full zero d… |
@ollama |
Company |
Original |
2026-11-03 |
15,482 |
236 |
21 |
41 |
4 |
33 |
| why Ollama Cloud has grown 200x since the start of the year 👇 @togethercompute @vipulved @jmorgan https://t.co/pZBH2NHt… |
@ollama |
Company |
Original |
2026-10-30 |
14,397 |
134 |
16 |
32 |
3 |
15 |
| Enterprise teams around the world (including Korea, where we'll be next week!) are using Ollama to transition their wor… |
@ollama |
Company |
Original |
2026-10-29 |
11,538 |
84 |
12 |
18 |
0 |
8 |
| Recent model updates from the past two weeks 👇
In Ollama’s cloud ☁️:
- Beam (free for a limited time!)
- Muse-spark-op… |
@ollama |
Company |
Original |
2026-10-29 |
46,630 |
635 |
51 |
68 |
6 |
154 |
| RT @ollama: why security teams use ollama to work with open models @togethercompute @vipulved @jmorgan https://t.co/ntr… |
@ollama |
Company |
Repost |
2026-10-29 |
-- |
0 |
8 |
0 |
0 |
0 |
| why security teams use ollama to work with open models @togethercompute @vipulved @jmorgan https://t.co/ntrVinG3zT |
@ollama |
Company |
Original |
2026-10-28 |
14,053 |
106 |
8 |
19 |
3 |
17 |
| 여러분, 안녕하세요! 🇰🇷
We are days away from our first trip to Seoul!
Come meet us and @friendliai on Nov 5th.
We would love t… |
@ollama |
Company |
Original |
2026-10-28 |
12,609 |
77 |
7 |
10 |
3 |
9 |
| Run the best frontier open models on Ollama's cloud today @CrusoeAI @mchiang0610 https://t.co/cZVOioTv66 |
@ollama |
Company |
Original |
2026-10-27 |
20,823 |
222 |
14 |
18 |
3 |
26 |
| RT @togethercompute: Two companies, one goal: open models that work for builders at any scale.
@jmorgan of @ollama an… |
@ollama |
Company |
Repost |
2026-10-27 |
1,734 |
0 |
5 |
0 |
0 |
0 |
| RT @maximelabonne: LFM3: new generation with six edge models
I'm super happy with LFM3-1.7B, it's an absolute (agentic… |
@ollama |
Company |
Repost |
2026-10-27 |
1,840 |
0 |
44 |
0 |
0 |
0 |
| LFM3 from @liquidai is on Ollama! Small models built to run anywhere and fine-tune on a single GPU:
- Text, vision, au… |
@ollama |
Company |
Original |
2026-10-27 |
50,839 |
895 |
69 |
50 |
15 |
292 |
| Defensive work shouldn’t mean sending sensitive data somewhere you don’t control. You can run open models locally with … |
@ollama |
Company |
Quote |
2026-10-23 |
17,648 |
235 |
14 |
39 |
2 |
22 |
| Nemotron 3.5 Bolt E4B 4GB from @NvidiaAI is now available on Ollama.
This new small open model is built for local assi… |
@ollama |
Company |
Original |
2026-10-23 |
43,073 |
678 |
41 |
32 |
10 |
180 |
| Nemotron 3.5 Bolt from @NVIDIAAI is live on Ollama.
This small vision-language model for fast local conversations, ima… |
@ollama |
Company |
Original |
2026-10-23 |
20,704 |
224 |
13 |
19 |
4 |
25 |
| RT @SparkLLM: Spark-X2.6-4B is here! Stronger coding, agents & long-context skills through improved post-training. … |
@ollama |
Company |
Repost |
2026-10-23 |
1,946 |
0 |
88 |
0 |
0 |
0 |
| enterprise AI is having its PC moment. @jmorgan on @thisweeknai with @Jason https://t.co/uPmCwWaPrh |
@ollama |
Company |
Original |
2026-10-22 |
12,762 |
72 |
6 |
17 |
2 |
5 |
| RT @CrusoeAI: New open models ship fast. Ollama's developers expect them on day one.
@ollama runs that workload on NVI… |
@ollama |
Company |
Repost |
2026-10-21 |
1,824 |
0 |
4 |
0 |
0 |
0 |
| Meet Flint from @Recursive_SI! A ~40B parameter MoE open model for fast, accurate agentic coding use case made to run o… |
@ollama |
Company |
Quote |
2026-10-21 |
40,440 |
515 |
37 |
59 |
10 |
219 |
| We've spent the last several months scaling our compute footprint right here in the U.S., and we got to see some of it … |
@ollama |
Company |
Original |
2026-10-20 |
14,238 |
122 |
13 |
15 |
4 |
9 |
| RT @CrusoeAI: San Francisco showed up! 🌉
@ollama's @jmorgan and @TrajectoryLabs' @MichaelElabd joined Crusoe's Erwan M… |
@ollama |
Company |
Repost |
2026-10-20 |
1,788 |
0 |
7 |
0 |
0 |
0 |
| Clef from @Cloudflare is on Ollama. Run it locally or in the cloud.
27B multimodal decision model, supports text and i… |
@ollama |
Company |
Original |
2026-10-20 |
24,902 |
267 |
21 |
22 |
3 |
56 |
| RT @ornith_: 🥳 Ornith 1.5 122B is now available on Ollama!
Hats off to our awesome friends at @ollama
🔗 https://t.co… |
@ollama |
Company |
Repost |
2026-10-20 |
1,880 |
0 |
12 |
0 |
0 |
0 |
| Ornith 1.5 122B is available on Ollama! Run it all locally on your device.
ollama run ornith-1.5:122b |
@ollama |
Company |
Quote |
2026-10-20 |
31,370 |
390 |
36 |
39 |
6 |
61 |
| For the next 3 days, in collaboration with @MiniMax_AI, MiniMax M3.1 Flash will be free on Ollama's Cloud!
Hosted in … |
@ollama |
Company |
Quote |
2026-10-20 |
47,295 |
736 |
39 |
43 |
19 |
148 |
| RT @MiniMax_AI: Day0 support from @ollama 🦙🤝🐰
M3.1 Flash, US-hosted, zero data retention, ready for your agents. Go bu… |
@ollama |
Company |
Repost |
2026-10-19 |
1,579 |
0 |
4 |
0 |
0 |
0 |
| MiniMax M3.1 Flash is on Ollama!
🔒 Hosted in the US and with zero data retention.
Fast coding and agentic workflows… |
@ollama |
Company |
Quote |
2026-10-19 |
65,054 |
408 |
29 |
46 |
7 |
48 |
| Ollama Cloud is always zero data retention, hosted in US and EU with no training. |
@ollama |
Company |
Original |
2026-10-17 |
43,970 |
988 |
50 |
65 |
9 |
84 |
| ✈ DeepSeek-V4.1-Flash-1017 is on Ollama! US-based hosting with zero data retention.
It's strong on agentic tasks whil… |
@ollama |
Company |
Quote |
2026-10-17 |
130,479 |
1,243 |
87 |
97 |
30 |
231 |
| Working on getting our US hosts up and running. Very soon! |
@ollama |
Company |
Quote |
2026-10-17 |
21,808 |
585 |
23 |
36 |
1 |
21 |
| RT @zeddotdev: In this video, Joseph asks Delta to configure itself to use @ollama as a custom OpenAI-compatible provid… |
@ollama |
Company |
Repost |
2026-10-17 |
1,804 |
0 |
6 |
0 |
0 |
0 |
| RT @tryreplicas: .@ollama is now an inference provider on Replicas. Run open models in Claude Code, Codex, OpenCode and… |
@ollama |
Company |
Repost |
2026-10-17 |
1,776 |
0 |
5 |
0 |
0 |
0 |
| 안녕하세요 🇰🇷
Bags packed. Ollama is headed to Seoul ✈️
Korea is one of the most innovative AI markets in the world, and w… |
@ollama |
Company |
Original |
2026-10-17 |
28,939 |
589 |
111 |
68 |
17 |
79 |
| We’re excited to be day 0 partners for @reflection_ai’s first open-weight model! For a limited time,
Beam is FREE on … |
@ollama |
Company |
Quote |
2026-10-16 |
105,780 |
302 |
30 |
44 |
8 |
62 |
| NVIDIA Nemotron 3.5 Bolt 74B-A9B 24GB is now on Ollama
This model vision-language model (VLM) is designed to run every… |
@ollama |
Company |
Original |
2026-10-15 |
19,815 |
299 |
20 |
28 |
9 |
59 |
| NVIDIA Nemotron 3.5 Super VL is now available on Ollama
This model combines reasoning and visual understanding across … |
@ollama |
Company |
Original |
2026-10-15 |
241,515 |
158 |
15 |
13 |
3 |
20 |
| Muse Spark Open is now rolled out to Pro, Max, Pay-as-you-go, and Teams plans. |
@ollama |
Company |
Quote |
2026-10-15 |
12,941 |
153 |
9 |
7 |
1 |
20 |
| Muse Spark Open is now on Ollama.
@Meta's open-weight model for coding and tool use, with a 1M-token context window.
… |
@ollama |
Company |
Original |
2026-10-15 |
115,282 |
570 |
42 |
52 |
11 |
77 |
| Amazing to see @AIatMeta launch the best US open-weight model so far!
The model will be available on Ollama shortly. 🫡 |
@ollama |
Company |
Quote |
2026-10-15 |
29,602 |
586 |
35 |
21 |
4 |
75 |
| Meet Ollama co-founder & CEO @jmorgan who speaks about open model adoption in the enterprise.
Watch the episode
👇 |
@ollama |
Company |
Quote |
2026-10-15 |
9,585 |
109 |
9 |
5 |
0 |
24 |
| ollama run lfm2.5:24b
https://t.co/MpidEmAorV |
@ollama |
Company |
Quote |
2026-10-15 |
21,664 |
288 |
27 |
24 |
4 |
84 |
| RT @flydotio: Want to use @ollama Cloud in a Sprite? We got you.
You can now access Ollama Cloud through our Sprites C… |
@ollama |
Company |
Repost |
2026-10-14 |
1,919 |
0 |
3 |
0 |
0 |
0 |
| RT @RealChrisSean: It was fun collaborating with the team at @ollama. :) |
@ollama |
Company |
Repost |
2026-10-14 |
1,704 |
0 |
3 |
0 |
0 |
0 |
| RT @FrancoisChauba1: Next YC Paper Club: Inference
Inference is no longer just: y = model.forward(x)
It has now bec… |
@ollama |
Company |
Repost |
2026-10-09 |
1,751 |
0 |
18 |
0 |
0 |
0 |
| RT @Windows: Tomorrow, see what’s next from Windows, @surface, and @NVIDIARTXSpark.
Tune in live at 10:00 AM PT: https… |
@ollama |
Company |
Repost |
2026-10-06 |
1,690 |
0 |
133 |
0 |
0 |
0 |
| .@GoogleDeepMind EmbeddingGemma 2 is now available on Ollama.
Made for consumer devices and is multimodal.
ollama p… |
@ollama |
Company |
Quote |
2026-10-06 |
29,978 |
646 |
44 |
18 |
4 |
143 |
| Excited about the new open model from @reflection_ai!
More US models coming to Ollama! |
@ollama |
Company |
Quote |
2026-10-05 |
34,645 |
619 |
37 |
27 |
4 |
100 |
| RT @CloudflareDev: ollama pull clef
open models for all. start building with @ollama and @cloudflare clef decision mode… |
@ollama |
Company |
Repost |
2026-10-03 |
1,739 |
0 |
15 |
0 |
0 |
0 |
| .@Cloudflare's decision models are available on Ollama!
Decision models allow you to classify an image, label a bug re… |
@ollama |
Company |
Original |
2026-10-03 |
63,152 |
1,127 |
128 |
53 |
25 |
476 |
| RT @lucataco: Clef Decision Models are now on @ollama https://t.co/UPDD5zegGm |
@ollama |
Company |
Repost |
2026-10-03 |
1,721 |
0 |
8 |
0 |
0 |
0 |
| RT @togethercompute: 3/ @zainhas and @parthsareen (Agents at @ollama) took the breakout stage on evaluating open models… |
@ollama |
Company |
Repost |
2026-10-02 |
1,647 |
0 |
1 |
0 |
0 |
0 |
| RT @CrusoeAI: Crusoe AI Talks returns to SF.
Wed Oct. 7: Join @ollama's @jmorgan and @TrajectoryLabs' @MichaelElabd f… |
@ollama |
Company |
Repost |
2026-10-02 |
1,684 |
0 |
1 |
0 |
0 |
0 |
| RT @HakanGecili2: @ollama Tested Tev1, Nimble and Laya on my pacman-arena game setup:
code: https://t.co/mSsvSaZHSq htt… |
@ollama |
Company |
Repost |
2026-09-30 |
1,704 |
0 |
5 |
0 |
0 |
0 |
| RT @sojoodi: I love decision models popularized by @typesafeai 's JEV but I also want to run it locally, especially for… |
@ollama |
Company |
Repost |
2026-09-30 |
1,711 |
0 |
12 |
0 |
0 |
0 |
| Ollama now supports Jev-like decision models all locally.
Use decision models like Nimble for tasks like ticket triagi… |
@ollama |
Company |
Original |
2026-09-30 |
646,479 |
4,547 |
595 |
159 |
115 |
2,673 |
| RT @CrusoeAI: Closed model, open model, or train your own?
📅 Wed, Oct 7
🕐 5 PM
📍 San Francisco
At our next AI Talk… |
@ollama |
Company |
Repost |
2026-09-24 |
1,758 |
0 |
3 |
0 |
0 |
0 |
| You can now add usage credits for paid cloud models without an Ollama subscription.
Add usage credits and pay as you g… |
@ollama |
Company |
Original |
2026-09-23 |
16,649 |
132 |
7 |
20 |
3 |
8 |
| Over the last few hours, some requests to the deepseek-v4.1-flash model on Ollama were charged at an incorrect rate, le… |
@ollama |
Company |
Original |
2026-09-22 |
49,954 |
535 |
12 |
59 |
8 |
23 |
| RT @togethercompute: coding agents are moving fast from prototype to production. the infrastructure question is what's … |
@ollama |
Company |
Repost |
2026-09-21 |
1,703 |
0 |
4 |
0 |
0 |
0 |
| RT @jmorgan: Many concerns this weekend about slowing down AI, some targeting open models.
We need to be responsible. … |
@ollama |
Company |
Repost |
2026-09-13 |
1,826 |
0 |
10 |
0 |
0 |
0 |
| RT @jmorgan: Small models are truly capable of the majority of conversational use cases and even a majority of difficul… |
@ollama |
Company |
Repost |
2026-09-13 |
1,896 |
0 |
4 |
0 |
0 |
0 |
| Amp users can now use Ollama's cloud models with Amp's new BYOK model routing.
No limits or fees for BYOK.
Build remo… |
@ollama |
Company |
Quote |
2026-09-12 |
33,126 |
233 |
11 |
18 |
3 |
52 |
| DeepSeek-V4.1-Flash is now fully rolled out and available on Ollama's cloud:
- Hosted in US & Europe
- Zero data reten… |
@ollama |
Company |
Quote |
2026-09-11 |
57,492 |
736 |
45 |
58 |
7 |
96 |
| DeepSeek-V4.1-Flash is now rolling out for Pro plan subscribers. |
@ollama |
Company |
Quote |
2026-09-11 |
40,027 |
500 |
21 |
37 |
5 |
14 |
| ChatGPT Desktop (the Codex app) can now be configured to use Ollama models. Download or update to Ollama 0.34 to get st… |
@ollama |
Company |
Original |
2026-09-11 |
102,942 |
1,343 |
95 |
53 |
17 |
526 |
| DeepSeek-V4.1-Flash is now being rolled out on Ollama's cloud, starting with Max and Team accounts.
We are quickly add… |
@ollama |
Company |
Quote |
2026-09-10 |
74,219 |
490 |
39 |
30 |
6 |
26 |
| Introducing off-peak hour token rates.
DeepSeek-V4-Flash and Pro are now half price outside of 12:00 to 18:00 UTC on w… |
@ollama |
Company |
Original |
2026-09-05 |
88,505 |
925 |
48 |
71 |
16 |
121 |
| RT @USWREMichael: American open weights/source is a national security imperative. |
@ollama |
Company |
Repost |
2026-09-04 |
1,766 |
0 |
83 |
0 |
0 |
0 |
| RT @paulg: It sounds like the shift back toward open weight models that I noticed among the startups in the summer batc… |
@ollama |
Company |
Repost |
2026-09-04 |
1,630 |
0 |
54 |
0 |
0 |
0 |
| RT @ycombinator: Open models are closing the intelligence gap, says @ollama's @jmorgan. That opens up a new opportunity… |
@ollama |
Company |
Repost |
2026-09-04 |
1,710 |
0 |
15 |
0 |
0 |
0 |
| RT @ycombinator: 🦙 @ollama is used by 9 million developers and 85% of the Fortune 500, giving co-founder and CEO Jeffre… |
@ollama |
Company |
Repost |
2026-09-04 |
1,739 |
0 |
39 |
0 |
0 |
0 |
| RT @Technovangelist: Stop typing @Ollama commands the old way.
Ollama’s new interactive menu makes it easier to discove… |
@ollama |
Company |
Repost |
2026-09-03 |
1,701 |
0 |
1 |
0 |
0 |
0 |
| Congrats to the team! Bullish on open models and all the partners we make along the way! ❤️
Let’s go |
@ollama |
Company |
Quote |
2026-09-03 |
31,459 |
386 |
12 |
15 |
1 |
17 |
| 🚀🚀🚀 can't wait for the Muse Spark open weight releases. ❤️
Thank you @finkd |
@ollama |
Company |
Quote |
2026-09-02 |
21,939 |
382 |
15 |
11 |
2 |
22 |
| Ollama’s Pro, Max, and Team plans now use transparent per-token pricing.
Based on your feedback, every plan includes … |
@ollama |
Company |
Original |
2026-09-01 |
298,115 |
828 |
67 |
226 |
62 |
166 |
| Ollama already support the Muse Code harness out of the box?
You can try it with models via Ollama (local and cloud):… |
@ollama |
Company |
Quote |
2026-09-01 |
31,589 |
216 |
12 |
29 |
2 |
15 |
| Try GLM 5.3! |
@ollama |
Company |
Quote |
2026-08-29 |
23,812 |
372 |
10 |
23 |
2 |
16 |
| GLM 5.3 and GLM 5.3 Flash (previously Ox Alpha) are fully rolled out on Ollama's cloud.
Private.
Fast.
US and Europe… |
@ollama |
Company |
Original |
2026-08-29 |
47,859 |
761 |
59 |
60 |
14 |
69 |
| We are rolling out GLM-5.3 on Ollama. Private. Fast. US and Europe hosted. No data retention.
Try Ollama's GLM-5.3-Fl… |
@ollama |
Company |
Quote |
2026-08-28 |
110,241 |
975 |
71 |
62 |
15 |
217 |
| RT @ZixuanLi_: GLM-5.3-Flash scores 57 on the Artificial Analysis Intelligence Index and is connected to GLM-5.3 along … |
@ollama |
Company |
Repost |
2026-08-26 |
1,787 |
0 |
61 |
0 |
0 |
0 |
| glm-5.3-flash will be available shortly on Ollama's cloud. |
@ollama |
Company |
Original |
2026-08-26 |
66,261 |
1,207 |
50 |
80 |
8 |
57 |
| RT @EliaAlberti: You can now run Claude Desktop fully on local models with one toggle.
Open @ollama on, pick a model. … |
@ollama |
Company |
Repost |
2026-08-26 |
1,804 |
0 |
4 |
0 |
0 |
0 |
| RT @ZixuanLi_: No reward hacking was found in GLM-5.2: solve the task, not the benchmark. |
@ollama |
Company |
Repost |
2026-08-26 |
1,812 |
0 |
26 |
0 |
0 |
0 |
| RT @chevonphillip: OMG! @ollama the real 🐐! https://t.co/DdAzdizypm |
@ollama |
Company |
Repost |
2026-08-26 |
1,851 |
0 |
2 |
0 |
0 |
0 |
| Ollama v0.33 is here!
You can now easily configure Claude Desktop to seamlessly work with Ollama as a third-party gat… |
@ollama |
Company |
Original |
2026-08-26 |
467,304 |
2,582 |
250 |
117 |
48 |
1,192 |
| IBM Granite 4.2 is now available on Ollama.
3B, 8B, 30B parameter open models made for enterprise agents.
This mode… |
@ollama |
Company |
Quote |
2026-08-25 |
19,563 |
162 |
15 |
11 |
4 |
50 |
| 🤯 Excited for all the models to come!
Ollama is exploding in token usage.
Better models, choice of apps/harness, an… |
@ollama |
Company |
Original |
2026-08-25 |
37,872 |
731 |
34 |
58 |
10 |
37 |
| .@poolsideai engineers were awesome to collaborate with to launch open models.
Excited for what’s to come to open mod… |
@ollama |
Company |
Quote |
2026-08-23 |
38,850 |
434 |
24 |
27 |
4 |
47 |
| Kimi K3 is now available on all Pro and Max subscriptions via included usage.
More models coming soon 🫡 |
@ollama |
Company |
Quote |
2026-08-21 |
57,457 |
702 |
48 |
48 |
9 |
60 |
| RT @friendliai: ‘Open Models, Production Agents’ is underway! Tonight means another event hosted at FriendliAI's San Fr… |
@ollama |
Company |
Repost |
2026-08-21 |
1,851 |
0 |
3 |
0 |
0 |
0 |
| Welcome @ATT to open models! |
@ollama |
Company |
Quote |
2026-08-21 |
17,788 |
213 |
14 |
9 |
0 |
11 |
| RT @_philschmid: Awesome Gemma is live on @github 🤗 A list of awesome Gemma resources, tools, and projects.
1. Model … |
@ollama |
Company |
Repost |
2026-08-20 |
1,652 |
0 |
19 |
0 |
0 |
0 |
| Kimi K3 is now rolled out to over half of the subscription base for included usage, and we're continuing to expand acce… |
@ollama |
Company |
Quote |
2026-08-20 |
76,189 |
651 |
43 |
57 |
10 |
72 |
| Congratulations to the whole @GoogleDeepMind Gemma team!
Gemma is one of the most popular open models.
It's been an… |
@ollama |
Company |
Quote |
2026-08-20 |
23,557 |
491 |
20 |
10 |
1 |
21 |
| RT @ornith_: 🐦Ornith 1.5 series models are now available on ollama!
🫡Thanks to our awesome friends at @ollama
👀Come … |
@ollama |
Company |
Repost |
2026-08-20 |
1,752 |
0 |
24 |
0 |
0 |
0 |
| .@Kimi_Moonshot Kimi K3 is starting to roll out on Ollama's cloud subscriptions.
We are working on improving Ollama's… |
@ollama |
Company |
Original |
2026-08-19 |
123,339 |
992 |
69 |
115 |
22 |
128 |
| Join us for a fun night this Thursday (August 20th) in San Francisco!
RSVP link below! 👇 |
@ollama |
Company |
Quote |
2026-08-17 |
17,821 |
80 |
6 |
10 |
1 |
6 |
| Ollama has the best performance for deepseek v4 flash on average.
For local only, you can try qwen3.8 that is optimiz… |
@ollama |
Company |
Quote |
2026-08-17 |
64,428 |
565 |
34 |
49 |
3 |
170 |
| The new DeepSeek-V4-Pro (0813) is now fully rolled out on Ollama's cloud and included in Pro and Max subscriptions.
ol… |
@ollama |
Company |
Original |
2026-08-15 |
75,118 |
1,060 |
48 |
69 |
9 |
97 |
| Ollama now supports the DeepSeek Harness.
ollama launch dsh
Run it completely in your own environment. It comes with … |
@ollama |
Company |
Quote |
2026-08-14 |
91,435 |
1,052 |
96 |
38 |
9 |
297 |
| It's been a pleasure to partner with the @Alibaba_Qwen team. |
@ollama |
Company |
Quote |
2026-08-14 |
40,397 |
594 |
22 |
16 |
1 |
19 |
| RT @Alibaba_Qwen: Qwen3.8-27B is available on @ollama ！Any harness you run, the model always delivers. Let's code toge… |
@ollama |
Company |
Repost |
2026-08-14 |
1,392 |
0 |
47 |
0 |
0 |
0 |
| Qwen 3.8 27B is now available on Ollama.
It's one of the best open models at this size, and made for agentic tasks an… |
@ollama |
Company |
Original |
2026-08-14 |
136,131 |
1,865 |
186 |
101 |
42 |
438 |
| See you soon! https://t.co/XZDsXc0FCu |
@ollama |
Company |
Original |
2026-08-14 |
56,049 |
1,089 |
33 |
25 |
9 |
52 |
| RT @louszbd: @elliotchen100 @ollama @Zai_org https://t.co/nI9RynnAge |
@ollama |
Company |
Repost |
2026-08-14 |
1,928 |
0 |
1 |
0 |
0 |
0 |
| Open models are improving at an unprecedented rate.
Congrats to the whole @Zai_org team.
Ollama will support GLM-5.… |
@ollama |
Company |
Quote |
2026-08-14 |
66,947 |
1,353 |
71 |
56 |
3 |
73 |
| Using @AIatMeta's Muse Glimmer all locally to process personal monthly credit card statements.
Your data belongs to y… |
@ollama |
Company |
Original |
2026-08-13 |
30,439 |
346 |
27 |
13 |
0 |
80 |
| You can now use Ollama as a provider in GitHub Copilot for JetBrains.
https://t.co/Rt8iSMYWaA https://t.co/SGZZ8VGCDU |
@ollama |
Company |
Original |
2026-08-12 |
18,440 |
194 |
19 |
18 |
1 |
28 |
| It's been exciting for Ollama to partner with @JensenHuang and the @NVIDIAAI team on launching open models.
Open mode… |
@ollama |
Company |
Quote |
2026-08-11 |
43,876 |
583 |
38 |
14 |
5 |
44 |
| NVIDIA Nemotron 3.5 Lighting is available on Ollama!
It's a 30B model made for always-on agents. All local.
Claude … |
@ollama |
Company |
Quote |
2026-08-11 |
77,528 |
792 |
79 |
44 |
9 |
188 |
| Muse Glimmer is now available to run with Ollama.
Available today via Ollama’s MLX engine with state-of-the-art-perfor… |
@ollama |
Company |
Quote |
2026-08-10 |
93,069 |
1,352 |
109 |
73 |
23 |
196 |
| Currently serving 200 tps+ output speed for DeepSeek-V4-Flash on Ollama's cloud with zero data retention (ZDR).
Have a… |
@ollama |
Company |
Quote |
2026-08-08 |
189,043 |
2,071 |
94 |
100 |
20 |
326 |
| DeepSeek-V4-Flash-0731 is now fully rolled out as the new default for deepseek-v4-flash on Ollama's cloud.
This model … |
@ollama |
Company |
Original |
2026-08-07 |
337,138 |
1,944 |
87 |
65 |
13 |
276 |
| DeepSeek-V4-Flash-0731 is Ollama's fastest growing model ever in token usage. We are scaling capacity in US & Europe.
… |
@ollama |
Company |
Original |
2026-08-04 |
388,886 |
5,612 |
286 |
146 |
54 |
1,043 |
| DeepSeek-V4-Flash-0731 is now over 2x faster than yesterday on Ollama's cloud! |
@ollama |
Company |
Quote |
2026-08-01 |
195,109 |
2,347 |
102 |
96 |
11 |
187 |
| DeepSeek-V4-Flash-0731 is now available on Ollama's cloud. This update substantially enhances the model's agentic capab… |
@ollama |
Company |
Original |
2026-08-01 |
334,765 |
1,975 |
131 |
92 |
26 |
342 |
| Excited to work with the @IntelBusiness team on enabling open models with Intel Core Ultra Series 3. |
@ollama |
Company |
Quote |
2026-07-30 |
34,622 |
247 |
16 |
30 |
0 |
10 |
| Kimi K3 is now available on Ollama’s cloud.
To use it with Claude Code, run:
ollama launch claude --model kimi-k3:clo… |
@ollama |
Company |
Quote |
2026-07-27 |
331,280 |
3,366 |
330 |
244 |
93 |
749 |
| Ollama is proud to sign @satyanadella's letter.
Our mission from day one has been to make open models accessible to ev… |
@ollama |
Company |
Quote |
2026-07-26 |
228,504 |
3,608 |
220 |
76 |
27 |
244 |
| Open 24/7! https://t.co/2B3YVOt6Jb |
@ollama |
Company |
Quote |
2026-07-26 |
42,427 |
843 |
35 |
18 |
3 |
22 |
| The demand for GLM-5.2 and other frontier-level open models has been surging on Ollama's cloud.
We're adding capacity … |
@ollama |
Company |
Original |
2026-07-24 |
218,795 |
1,818 |
79 |
83 |
28 |
163 |
| Open models matter.
Ollama works hard with the model creators, hardware partners, and most importantly developers bu… |
@ollama |
Company |
Quote |
2026-07-24 |
113,043 |
3,169 |
256 |
69 |
16 |
181 |
| Ollama's @jmorgan joined Yahoo Finance to talk about why Fortune 500 companies are shifting to open-source models for l… |
@ollama |
Company |
Original |
2026-07-23 |
18,423 |
119 |
17 |
10 |
2 |
25 |
| Ollama 0.32.1 includes significant improvements to Gemma 4's tool calling, making it much more reliable in coding agent… |
@ollama |
Company |
Quote |
2026-07-17 |
99,672 |
848 |
99 |
47 |
9 |
300 |
| Open models are already being used in the enterprise.
Over 85% of the Fortune 500 companies already use Ollama to ful… |
@ollama |
Company |
Original |
2026-07-16 |
43,052 |
445 |
56 |
33 |
9 |
77 |
| Ollama is back in NYC today!
It's exciting to see more people and businesses realize the benefits of open models! Own… |
@ollama |
Company |
Original |
2026-07-15 |
28,838 |
508 |
38 |
30 |
5 |
19 |
| You can use OpenCode Desktop with Ollama!
Try it with the top open models! https://t.co/I3VSgOCRCo |
@ollama |
Company |
Quote |
2026-07-15 |
115,702 |
1,091 |
95 |
28 |
5 |
365 |
| U.S. open-source models are quickly gaining ground.
@Nvidia's newest Nemotron Ultra is fast growing on Ollama and unl… |
@ollama |
Company |
Original |
2026-07-14 |
73,908 |
424 |
38 |
23 |
7 |
74 |
| @jmorgan was on @tbpn this week to discuss Ollama's Series B fundraise and why open models are quickly becoming the def… |
@ollama |
Company |
Original |
2026-07-12 |
38,047 |
119 |
13 |
7 |
3 |
15 |
| Token usage beginning to tip towards open models.
Ollama’s @jmorgan and Peter Fenton predict that a supermajority of … |
@ollama |
Company |
Quote |
2026-07-10 |
34,502 |
261 |
29 |
23 |
1 |
34 |
| Watch Ollama's @jmorgan and @peterfenton on @CNBC with @dee_bosa at 12pm PT / 3pm ET to discuss "The Post-Frontier Era… |
@ollama |
Company |
Quote |
2026-07-09 |
17,302 |
69 |
5 |
9 |
0 |
7 |
| .@jmorgan will be live on TBPN today. |
@ollama |
Company |
Quote |
2026-07-09 |
16,059 |
55 |
3 |
6 |
0 |
2 |
| Big day for Ollama! When we started, open models and the open source AI ecosystem were in their early days with few bel… |
@ollama |
Company |
Original |
2026-07-09 |
334,163 |
2,048 |
238 |
209 |
109 |
219 |
| See you tomorrow! https://t.co/ZBeXoZWsCO |
@ollama |
Company |
Original |
2026-07-09 |
51,323 |
822 |
26 |
54 |
16 |
25 |
| GLM-5.2 on Ollama's cloud just got more capacity in US & Europe!
Ollama's cloud for GLM 5.2 consistently delivers bet… |
@ollama |
Company |
Original |
2026-07-08 |
66,706 |
785 |
44 |
51 |
14 |
115 |
| Congratulations to our friends at @togethercompute. Exciting moment for open models!! |
@ollama |
Company |
Quote |
2026-07-01 |
29,438 |
174 |
8 |
5 |
3 |
18 |
| Gemma 4 is now nearly 90% faster on Apple Silicon with Ollama using MLX!
The speedup comes from improved multi-token p… |
@ollama |
Company |
Original |
2026-07-01 |
210,320 |
3,396 |
266 |
65 |
52 |
1,310 |
| Run Ornith with Ollama:
ollama run ornith
For coding, use it with Claude or Pi:
ollama launch claude --model ornith
… |
@ollama |
Company |
Quote |
2026-06-27 |
138,356 |
1,324 |
117 |
51 |
7 |
666 |
| Let’s go open models! ❤️ |
@ollama |
Company |
Quote |
2026-06-21 |
81,492 |
1,105 |
49 |
33 |
4 |
56 |
| Let’s go open models! ❤️ |
@ollama |
Company |
Quote |
2026-06-20 |
25,129 |
211 |
9 |
12 |
1 |
8 |
| Let’s go open models! ❤️ |
@ollama |
Company |
Quote |
2026-06-20 |
178,461 |
2,243 |
175 |
43 |
7 |
497 |
| GLM 5.2 on Ollama's cloud just doubled GPU capacity to handle the volume of usage!
This is all US based, and running … |
@ollama |
Company |
Original |
2026-06-18 |
539,631 |
5,200 |
292 |
144 |
54 |
922 |
| Let's go open models! ❤️ |
@ollama |
Company |
Quote |
2026-06-18 |
47,630 |
471 |
34 |
10 |
2 |
89 |
| let's go open models! ❤️ |
@ollama |
Company |
Quote |
2026-06-17 |
70,751 |
1,183 |
49 |
22 |
6 |
221 |
| let's go open models! ❤️ |
@ollama |
Company |
Quote |
2026-06-17 |
40,852 |
552 |
20 |
22 |
1 |
46 |
| You can use GLM-5.2 and Kimi-K2.7-Code in Codex with Ollama!
ollama launch codex
ollama launch codex-app |
@ollama |
Company |
Quote |
2026-06-17 |
81,492 |
1,138 |
82 |
36 |
4 |
360 |
| wow. |
@ollama |
Company |
Quote |
2026-06-16 |
179,770 |
2,113 |
108 |
21 |
4 |
458 |
| 🤯 GLM-5.2 is here — built for long-horizon coding and agentic tasks, now with a solid 1M-token context.
The strongest… |
@ollama |
Company |
Quote |
2026-06-16 |
229,559 |
2,644 |
259 |
114 |
52 |
698 |
| open models. ❤️ |
@ollama |
Company |
Original |
2026-06-16 |
221,341 |
7,174 |
348 |
159 |
26 |
232 |
| Ollama now supports @cline CLI with the ability to run parallel tasks via the Kanban feature.
Cline is a coding agent … |
@ollama |
Company |
Original |
2026-06-15 |
37,061 |
287 |
28 |
15 |
7 |
102 |
| .@Kimi_Moonshot's kimi-k2.7-code is now available on Ollama's cloud!
On Ollama's cloud, this model is hosted in the U… |
@ollama |
Company |
Quote |
2026-06-13 |
63,456 |
625 |
62 |
35 |
14 |
113 |
| Use Ollama with Hermes Desktop by @NousResearch.
Hermes Desktop brings the same agent (its multi-agent engine, self-i… |
@ollama |
Company |
Original |
2026-06-09 |
54,326 |
895 |
118 |
35 |
10 |
483 |
| Gemma 4 Quantization-Aware Training (QAT) weights are now available on Ollama!
They reduce memory requirements while … |
@ollama |
Company |
Quote |
2026-06-05 |
112,277 |
1,434 |
158 |
42 |
14 |
711 |
| ollama run gemma4:12b
Gemma 4 12B is updated on Ollama, and available across all platforms!
Try it on:
Claude Code… |
@ollama |
Company |
Quote |
2026-06-04 |
75,155 |
1,142 |
112 |
52 |
9 |
393 |
| NVIDIA’s Nemotron 3 Ultra is available on Ollama’s cloud!
Try it 👇
Claude Code:
ollama launch claude --model nemot… |
@ollama |
Company |
Quote |
2026-06-04 |
44,369 |
538 |
48 |
42 |
7 |
148 |
| .@GoogleDeepMind's Gemma 4 - 12B is available on Ollama!
Chat:
ollama run gemma4:12b-mlx
Hermes Agent:
ollama lau… |
@ollama |
Company |
Original |
2026-06-03 |
66,963 |
1,248 |
132 |
54 |
16 |
405 |
| You can use Hermes Desktop with Ollama using local or cloud models.
Get started 👇👇👇 |
@ollama |
Company |
Quote |
2026-06-03 |
85,042 |
1,104 |
99 |
34 |
7 |
343 |
| Excited for Ollama to be working with @nvidia for the NVIDIA RTX Spark launch! https://t.co/ONIRsKQ5EU |
@ollama |
Company |
Quote |
2026-06-02 |
33,924 |
587 |
25 |
18 |
3 |
32 |
| .@MiniMax_AI M3 model is available on Ollama's Cloud!
In partnership with MiniMax, the M3 model on Ollama's Cloud is … |
@ollama |
Company |
Quote |
2026-06-01 |
49,290 |
530 |
47 |
42 |
7 |
83 |
| 😍 |
@ollama |
Company |
Quote |
2026-05-29 |
63,791 |
757 |
14 |
26 |
4 |
28 |
| OpenJarvis: a local-first personal AI is now available to run with Ollama
Built by Stanford’s @HazyResearch and Scalin… |
@ollama |
Company |
Original |
2026-05-29 |
222,740 |
2,491 |
368 |
62 |
36 |
2,551 |
| We just added significantly more NVIDIA Blackwell GPUs to better serve GLM-5.1 model on Ollama's cloud.
We have been … |
@ollama |
Company |
Original |
2026-05-15 |
76,886 |
877 |
62 |
90 |
11 |
176 |
| Ollama now supports Codex app!
To try it, update to the latest Ollama 0.24, and run:
ollama launch codex-app
Selec… |
@ollama |
Company |
Original |
2026-05-15 |
722,840 |
3,200 |
379 |
129 |
145 |
1,797 |
| 🤯 Ollama now supports Claude Desktop via Claude’s built-in third party inference.
ollama launch claude-desktop
This a… |
@ollama |
Company |
Original |
2026-05-04 |
483,160 |
4,462 |
492 |
173 |
106 |
2,338 |
| Nemotron 3 Nano Omni is available locally on Ollama!
This requires the latest Ollama 0.22 release. |
@ollama |
Company |
Quote |
2026-04-28 |
51,455 |
417 |
41 |
37 |
2 |
87 |
| First open-weight model from @poolsideai! Apache license, and available on Ollama to try.
👇👇👇 model page |
@ollama |
Company |
Quote |
2026-04-28 |
46,750 |
368 |
37 |
7 |
1 |
106 |
| We are now enabling a queue for DeepSeek v4 Pro, expect longer time-to-first-token instead of degrading service.
plea… |
@ollama |
Company |
Original |
2026-04-27 |
39,468 |
749 |
33 |
65 |
5 |
39 |
| DeepSeek v4 Pro is now on Ollama's cloud! 🚀🚀🚀
Try it with Claude Code:
ollama launch claude --model deepseek-v4-pro:cl… |
@ollama |
Company |
Original |
2026-04-27 |
106,420 |
1,605 |
170 |
120 |
29 |
311 |
| ❤️ @ying11231, @BanghuaZ and @lmsysorg @sgl_project @radixark
Let's go DeepSeek v4 Pro! |
@ollama |
Company |
Quote |
2026-04-27 |
23,002 |
220 |
20 |
10 |
1 |
13 |
| deepseek-v4-flash is now available on Ollama's cloud! Hosted in the US.
Try it with Claude Code:
ollama launch claud… |
@ollama |
Company |
Quote |
2026-04-24 |
151,651 |
1,535 |
146 |
88 |
19 |
381 |
| Let's go DeepSeek v4!!! 🚗🚀 |
@ollama |
Company |
Quote |
2026-04-24 |
26,236 |
405 |
28 |
10 |
1 |
41 |
| 🐳Ollama is working to have DeepSeek-V4-Pro and Flash available on Ollama's cloud. |
@ollama |
Company |
Quote |
2026-04-24 |
87,898 |
1,947 |
126 |
90 |
9 |
150 |
| Qwen 3.6 27B model is available on Ollama!
Use it with all the integrations in Ollama or chat with the model.
Chat … |
@ollama |
Company |
Quote |
2026-04-22 |
169,043 |
1,203 |
116 |
62 |
16 |
385 |
| ❤️❤️❤️ |
@ollama |
Company |
Quote |
2026-04-21 |
13,781 |
34 |
0 |
1 |
0 |
1 |
| Scaling up Kimi K2.6 with more NVIDIA Blackwell GPUs! Will be adding more in the coming days.
Try it with OpenClaw:
… |
@ollama |
Company |
Original |
2026-04-21 |
34,853 |
645 |
54 |
51 |
9 |
127 |
| Kimi Kimi 。 Kimi Kimi Kimi Kimi Kimi Kimi
ollama run kimi-k2.6:cloud |
@ollama |
Company |
Original |
2026-04-21 |
13,291 |
246 |
16 |
21 |
1 |
16 |
| Kimi K2.6 raises the bar for open-source models.
🦙 available on Ollama's cloud!
Try it with OpenClaw:
ollama launc… |
@ollama |
Company |
Quote |
2026-04-20 |
208,034 |
1,911 |
170 |
89 |
29 |
715 |
| ollama launch copilot
Ollama now supports GitHub's Copilot CLI, the terminal agent that works directly with repositor… |
@ollama |
Company |
Original |
2026-04-19 |
143,077 |
860 |
110 |
50 |
23 |
250 |
| Build your own assistant with @NVIDIAAI.
❤️ |
@ollama |
Company |
Quote |
2026-04-18 |
306,333 |
2,058 |
128 |
15 |
2 |
1,922 |
| ollama launch hermes
Ollama 0.21 includes supports Hermes Agent, the self-improving AI agent built by @NousResearch. |
@ollama |
Company |
Original |
2026-04-17 |
312,766 |
2,616 |
262 |
96 |
51 |
993 |
| Qwen 3.6 is here, and open-source! Run it locally with improved agentic coding capabilities.
Try it with Claude Code: … |
@ollama |
Company |
Quote |
2026-04-16 |
490,637 |
2,026 |
203 |
104 |
23 |
858 |
| ollama launch claude --model glm-5.1:cloud
(We are rushing to get more capacity 🙏🙏🙏) |
@ollama |
Company |
Quote |
2026-04-15 |
44,535 |
432 |
13 |
25 |
1 |
88 |
| We are rushing to add more capacity to Ollama's cloud.
Please be patient with us as we add more GPUs. 🙏 https://t.co/… |
@ollama |
Company |
Original |
2026-04-15 |
40,939 |
917 |
47 |
88 |
8 |
38 |
| Ollama and Google Gemma team is hosting an Ollama Gemma Day in Palo Alto tomorrow night (Wednesday, April 15th at 6pm).… |
@ollama |
Company |
Original |
2026-04-14 |
35,749 |
283 |
40 |
11 |
3 |
34 |
| We are working through the night to continue to scale capacity for Ollama's cloud.
Apologies if you see any performan… |
@ollama |
Company |
Original |
2026-04-13 |
21,935 |
512 |
26 |
35 |
4 |
19 |
| Ollama 0.20.6 is here with improved Gemma 4 tool calling!
more improvements to come for Gemma 4! https://t.co/pKun1uC… |
@ollama |
Company |
Original |
2026-04-13 |
107,163 |
1,881 |
134 |
63 |
22 |
299 |
| MiniMax M2.7 is available on Ollama's cloud, and is licensed for commercial usage.
Use it with OpenClaw:
ollama lau… |
@ollama |
Company |
Quote |
2026-04-12 |
271,203 |
1,188 |
100 |
73 |
14 |
492 |
| .@steipete has been an amazing supporter of open models and local models. This is even before the rise of OpenClaw. 🦞
… |
@ollama |
Company |
Quote |
2026-04-08 |
34,128 |
562 |
18 |
22 |
3 |
32 |
| We are hosting Ollama's MLX meetup this Thursday night (April 9th) at Ollama's office in Palo Alto at 6pm.
Come meet … |
@ollama |
Company |
Original |
2026-04-07 |
49,697 |
245 |
23 |
14 |
3 |
30 |
| GLM-5.1 is here!
Try it on OpenClaw🦞🦞🦞
ollama launch openclaw --model glm-5.1:cloud
Claude Code
ollama launch cla… |
@ollama |
Company |
Quote |
2026-04-07 |
147,725 |
1,663 |
147 |
73 |
22 |
703 |
| 🦞Ollama's cloud is one of the best places to run OpenClaw.
$20 plan is enough for most day to day OpenClaw usage wit… |
@ollama |
Company |
Quote |
2026-04-07 |
117,674 |
841 |
53 |
60 |
7 |
439 |
| Ollama's cloud is now the best place to run Gemma 4 in the cloud!
Available through a subscription for developers and… |
@ollama |
Company |
Original |
2026-04-06 |
126,734 |
2,260 |
230 |
97 |
25 |
876 |
| All usage refresh has rolled out on Ollama's cloud! Let's go open models!
It's time to give your 🦞 an open home. |
@ollama |
Company |
Quote |
2026-04-04 |
40,234 |
459 |
31 |
26 |
4 |
40 |
| Starting tomorrow at 11am PT, Ollama subscriptions usage will refresh to cover increased usage of third-party tools lik… |
@ollama |
Company |
Original |
2026-04-04 |
240,286 |
2,631 |
182 |
123 |
63 |
383 |
| 🦞Ollama's cloud is one of the best places to run OpenClaw.
$20 plan is enough for most day to day OpenClaw usage with … |
@ollama |
Company |
Quote |
2026-04-04 |
650,191 |
3,362 |
313 |
186 |
53 |
1,966 |
| .@GoogleDeepMind Gemma 4 is here with state-of-the-art models targeting edge and workstations.
Requires Ollama 0.20+ t… |
@ollama |
Company |
Quote |
2026-04-02 |
384,285 |
3,814 |
443 |
97 |
49 |
1,455 |
| 💎💎💎💎 |
@ollama |
Company |
Quote |
2026-04-02 |
93,544 |
521 |
9 |
13 |
12 |
24 |
| Ollama is now updated to run the fastest on Apple silicon, powered by MLX, Apple's machine learning framework.
This c… |
@ollama |
Company |
Original |
2026-03-31 |
790,392 |
5,767 |
715 |
294 |
212 |
2,877 |
| ollama launch pi --model kimi-k2.5:cloud
Ollama can now launch Pi, the coding agent that powers OpenClaw.
Designed t… |
@ollama |
Company |
Original |
2026-03-30 |
86,180 |
1,078 |
146 |
57 |
15 |
526 |
| Visual Studio Code now integrates with Ollama via GitHub Copilot.
If you have Ollama installed, any local or cloud mo… |
@ollama |
Company |
Original |
2026-03-26 |
348,544 |
4,627 |
497 |
116 |
68 |
1,542 |
| Ollama's cloud is now handling the current demand.
We continue to monitor the traffic to further scale up when necess… |
@ollama |
Company |
Original |
2026-03-25 |
15,270 |
188 |
13 |
14 |
1 |
21 |
| We are scaling Ollama's cloud. So sorry for anyone hitting errors. https://t.co/BqcGg4JujT |
@ollama |
Company |
Original |
2026-03-25 |
18,701 |
249 |
17 |
19 |
4 |
20 |
| Ollama's Pro plan now has an annual option. For $200/year, you get 2 months free.
Power OpenClaw, Claude Code, and mor… |
@ollama |
Company |
Original |
2026-03-24 |
83,840 |
711 |
55 |
50 |
10 |
209 |
| Nemotron-Cascade-2 is now available to run with Ollama.
ollama run nemotron-cascade-2
To run it locally with OpenClaw… |
@ollama |
Company |
Original |
2026-03-20 |
41,479 |
558 |
64 |
30 |
7 |
272 |
| MiniMax-M2.7 is now available on Ollama's cloud.
made for coding and agentic tasks
🖥️ Try it inside Claude Code: … |
@ollama |
Company |
Quote |
2026-03-18 |
106,191 |
713 |
81 |
39 |
15 |
322 |
| Nemotron 3 Nano 4B is now available to run via Ollama:
ollama run nemotron-3-nano:4b
Try it with Pi, the minimal agen… |
@ollama |
Company |
Original |
2026-03-17 |
65,932 |
1,063 |
114 |
48 |
13 |
623 |
| Ollama 0.18.1 is here!
🌐 Web search and fetch in OpenClaw
Ollama now ships with web search and web fetch plugin for … |
@ollama |
Company |
Original |
2026-03-17 |
151,807 |
1,702 |
210 |
70 |
32 |
1,231 |
| Ollama is now a provider inside CodexBar!
Thank you @steipete for the awesome work! |
@ollama |
Company |
Quote |
2026-03-17 |
108,010 |
592 |
52 |
24 |
2 |
137 |
| Ollama is now an official provider for OpenClaw.
openclaw onboard --auth-choice ollama
All models from Ollama will … |
@ollama |
Company |
Original |
2026-03-16 |
441,759 |
6,339 |
676 |
314 |
136 |
2,556 |
| Ollama's cloud is updated to use NVIDIA's latest data center hardware: B300 for Kimi K2.5 and GLM-5 models.
This signi… |
@ollama |
Company |
Original |
2026-03-14 |
42,693 |
657 |
40 |
56 |
7 |
90 |
| Are you attending @NVIDIAGTC?
Ollama + NVIDIA are doing a developer session on local AI on RTX AI PCs
Come learn how… |
@ollama |
Company |
Original |
2026-03-13 |
38,032 |
445 |
41 |
23 |
3 |
94 |
| NVIDIA Nemotron 3 Super is now available on Ollama.
ollama run nemotron-3-super:cloud
🦞Try it with OpenClaw:
ollama… |
@ollama |
Company |
Quote |
2026-03-11 |
178,229 |
1,144 |
142 |
72 |
20 |
697 |
| Ollama can now run prompts on a schedule in Claude Code. Stay on top of work by setting automated tasks or reminders.
… |
@ollama |
Company |
Original |
2026-03-10 |
122,508 |
1,628 |
145 |
70 |
12 |
821 |
| The Qwen 3.5 small model series is now available
ollama run qwen3.5:9b
ollama run qwen3.5:4b
ollama run qwen3.5:2b
… |
@ollama |
Company |
Quote |
2026-03-02 |
332,703 |
3,264 |
350 |
95 |
42 |
1,129 |
| A big milestone @MiniMax_AI! Open weight models like M2.5 are beginning handle agentic tasks people used to trust only … |
@ollama |
Company |
Quote |
2026-03-02 |
73,601 |
730 |
56 |
26 |
4 |
174 |
| Ollama can now run subagents in OpenCode
Parallelize tasks which require longer context windows like research, refacto… |
@ollama |
Company |
Original |
2026-02-28 |
126,328 |
1,609 |
172 |
55 |
17 |
845 |
| Ollama can now launch Pi, a minimal coding agent which you can customize for your workflow
ollama launch pi
You can e… |
@ollama |
Company |
Original |
2026-02-26 |
191,514 |
1,507 |
202 |
54 |
24 |
922 |
| Ollama now supports vision capabilities in OpenClaw
ollama launch openclaw --model kimi-k2.5:cloud
OpenClaw can now s… |
@ollama |
Company |
Original |
2026-02-26 |
33,190 |
545 |
60 |
26 |
3 |
225 |
| Qwen 3.5 family is here!
> vision built-in, and can outperform previous VL models
> designed to be more efficient
> e… |
@ollama |
Company |
Quote |
2026-02-25 |
140,750 |
998 |
99 |
50 |
12 |
272 |
| CastFox runs Gemma 3n using Ollama for processing English, Japanese, and Korean audio. |
@ollama |
Company |
Quote |
2026-02-24 |
21,929 |
236 |
25 |
7 |
2 |
66 |
| ollama run lfm2:24b-a2b
.@liquidai's latest on-device model is here!
It's the largest LFM2 model yet, and is designe… |
@ollama |
Company |
Quote |
2026-02-24 |
32,648 |
296 |
42 |
13 |
3 |
101 |
| Ollama 0.17 makes it much simpler to use open models with @openclaw
Try it with:
ollama launch openclaw
Tutorial… |
@ollama |
Company |
Original |
2026-02-24 |
201,620 |
1,882 |
227 |
94 |
29 |
1,469 |
| Ollama 0.16.3 is out with Cline and Pi integrations out of the box.
Try it with:
@cline:
ollama launch cline
Pi:
o… |
@ollama |
Company |
Original |
2026-02-20 |
78,072 |
362 |
37 |
21 |
8 |
99 |
| Ollama now supports subagents and web search in Claude Code!
Subagents can run tasks in parallel, such as file search… |
@ollama |
Company |
Original |
2026-02-17 |
84,180 |
982 |
132 |
55 |
20 |
478 |
| Happy lunar new year! https://t.co/Pt5XcSM4ex |
@ollama |
Company |
Original |
2026-02-16 |
55,553 |
929 |
66 |
70 |
11 |
29 |
| ollama run qwen3.5:cloud
Qwen3.5-397B-A17B is the first open-weight model in the series.
It's available on Ollama's… |
@ollama |
Company |
Quote |
2026-02-16 |
85,846 |
502 |
56 |
29 |
6 |
85 |
| love. https://t.co/qGJyJ69hDT |
@ollama |
Company |
Original |
2026-02-14 |
24,153 |
645 |
38 |
27 |
5 |
28 |
| ❤️ We are partnering with @MiniMax_AI to give Ollama users free usage of MiniMax M2.5 for the next couple of days!
ol… |
@ollama |
Company |
Quote |
2026-02-12 |
440,166 |
4,082 |
344 |
152 |
63 |
2,574 |
| MiniMax M2.5 is on Ollama's cloud!
ollama run minimax-m2.5:cloud
Use MiniMax M2.5 with OpenCode, Claude Code, Codex… |
@ollama |
Company |
Quote |
2026-02-12 |
79,075 |
603 |
49 |
22 |
12 |
241 |
| GLM 5 on Ollama's cloud has increased capacity now and a higher speed!
Full sized model to use with your tools!
ollam… |
@ollama |
Company |
Quote |
2026-02-12 |
22,385 |
244 |
27 |
17 |
5 |
47 |
| We are working on increasing the capacity on Ollama's cloud.
Sorry for the wait! https://t.co/aYqh40oSVH |
@ollama |
Company |
Original |
2026-02-11 |
151,468 |
552 |
26 |
34 |
7 |
41 |
| ❤️ GLM-5 is on Ollama's cloud! It's free to start, and with higher limits available on the paid plans.
ollama run glm-… |
@ollama |
Company |
Quote |
2026-02-11 |
190,883 |
1,725 |
169 |
74 |
19 |
832 |
| 🤯 Wow! In one prompt Qwen3-Coder-Next generated a fully working flappy birds game in HTML.
(0:05) Claude Code with Qw… |
@ollama |
Company |
Original |
2026-02-06 |
117,689 |
693 |
70 |
36 |
12 |
382 |
| ollama run qwen3-coder-next
Run Qwen3-Coder-Next completely free, locally on your computer.
It's built for coding ag… |
@ollama |
Company |
Quote |
2026-02-04 |
190,517 |
1,446 |
155 |
51 |
22 |
925 |
| ollama pull glm-ocr
All local. You own your data.
GLM-OCR delivers state-of-the-art performance for document understa… |
@ollama |
Company |
Quote |
2026-02-03 |
161,705 |
1,702 |
174 |
38 |
16 |
1,284 |
| Make it easy to use @openclaw with Ollama launch to connect with local models that can run on your own device.
1. Ins… |
@ollama |
Company |
Original |
2026-02-02 |
175,910 |
2,029 |
248 |
107 |
34 |
1,895 |
| .@allen_ai team has made Sera available on Ollama!
ollama run nishtahir/sera |
@ollama |
Company |
Quote |
2026-01-29 |
27,618 |
252 |
29 |
9 |
3 |
113 |
| 🤯🤯🤯 @nvidia is partnering with Ollama to give one lucky member a chance to win a golden ticket to #NVIDIAGTC
Includes… |
@ollama |
Company |
Original |
2026-01-28 |
57,086 |
546 |
27 |
26 |
5 |
140 |
| Win a golden ticket to NVIDIA GTC!
Ollama 🤝 NVIDIA
❤️ |
@ollama |
Company |
Quote |
2026-01-28 |
26,229 |
78 |
2 |
6 |
0 |
10 |
| 🎉🎉🎉 Kimi K2.5 is on Ollama's cloud
ollama run kimi-k2.5:cloud
You can connect it to Claude Code, Codex, OpenCode, C… |
@ollama |
Company |
Quote |
2026-01-27 |
543,483 |
4,906 |
368 |
121 |
42 |
2,990 |
| Build your own personal assistant with @openclaw
and Ollama using your models!
ollama launch clawdbot
Thank you for b… |
@ollama |
Company |
Original |
2026-01-27 |
231,904 |
3,451 |
309 |
102 |
46 |
2,237 |
| Ollama is here with image generation!
ollama run x/z-image-turbo
ollama run x/flux2-klein
In the latest release we'… |
@ollama |
Company |
Original |
2026-01-21 |
93,214 |
1,280 |
227 |
50 |
30 |
652 |
| ollama run lfm2.5-thinking
LFM 2.5 thinking is now available on Ollama, and can be plugged into over 40,000 integratio… |
@ollama |
Company |
Quote |
2026-01-20 |
40,486 |
378 |
43 |
15 |
5 |
119 |
| ollama run glm-4.7-flash
GLM-4.7-flash is available in Ollama v0.14.3+ (currently in pre-release)
Link to download a… |
@ollama |
Company |
Quote |
2026-01-19 |
113,030 |
1,019 |
113 |
36 |
13 |
428 |
| Ollama now has Anthropic API compatibility.
🦙 This enables tools like Claude Code to be used with open-source models. … |
@ollama |
Company |
Original |
2026-01-17 |
591,800 |
6,244 |
752 |
180 |
162 |
3,025 |
| ollama run translategemma
TranslateGemma is available on Ollama. Now you can use it in apps to translate between 55 l… |
@ollama |
Company |
Quote |
2026-01-16 |
137,435 |
1,322 |
151 |
25 |
13 |
683 |
| The latest Android Studio has Ollama support. https://t.co/0r1FBaZY0q |
@ollama |
Company |
Quote |
2026-01-16 |
47,855 |
546 |
40 |
11 |
2 |
71 |
| Open models can be used with OpenAI's Codex CLI through Ollama!
All you need to do is:
codex --oss
It can load up… |
@ollama |
Company |
Quote |
2026-01-16 |
71,790 |
569 |
79 |
19 |
12 |
238 |
| Ollama now supports Open Responses! |
@ollama |
Company |
Quote |
2026-01-15 |
159,997 |
868 |
84 |
14 |
3 |
251 |
| We are hosting our first meetup at Ollama's office in Palo Alto - Wednesday, January 14th at 6pm
Join us to see Oll… |
@ollama |
Company |
Original |
2026-01-12 |
20,684 |
144 |
13 |
7 |
7 |
11 |
| Lots of updates in open source tools! So much more updates coming to Ollama this year.
Let's go! 😍😍
https://t.co/HbQ… |
@ollama |
Company |
Original |
2026-01-06 |
10,830 |
150 |
9 |
11 |
0 |
18 |
| Merry Christmas!! 🎄🎄🎄 https://t.co/mAEy2HPrV1 |
@ollama |
Company |
Original |
2025-12-25 |
12,389 |
340 |
20 |
11 |
3 |
7 |
| .@Zai_org's GLM 4.7 is now on Ollama!
ollama run glm-4.7:cloud
Model page:
https://t.co/CmcXLJ1uyA https://t.co/F… |
@ollama |
Company |
Original |
2025-12-23 |
13,525 |
198 |
24 |
6 |
2 |
30 |
| .@minimax_ai's M2.1 model is now available on Ollama!
ollama run minimax-m2.1:cloud
It's now updated to perform muc… |
@ollama |
Company |
Original |
2025-12-23 |
23,747 |
191 |
23 |
6 |
1 |
43 |
| 🌎 Google's FunctionGemma is 270M model that's fine-tuned by Google for function calling.
Try it on Ollama's latest v0… |
@ollama |
Company |
Quote |
2025-12-18 |
46,648 |
374 |
41 |
13 |
6 |
143 |
| ⚡️ Gemini 3 Flash is now available on Ollama's cloud:
ollama run gemini-3-flash-preview:cloud |
@ollama |
Company |
Quote |
2025-12-17 |
23,286 |
170 |
16 |
12 |
1 |
30 |
| .@nvidia Nemotron 3 Nano is now available on Ollama!
Local
ollama run nemotron-3-nano
Cloud
ollama run nemotron-3-n… |
@ollama |
Company |
Quote |
2025-12-16 |
32,089 |
210 |
24 |
6 |
2 |
49 |
| Olmo 3.1 and 3 from @allen_ai models are available on Ollama.
7B Instruct:
ollama run olmo-3:7b-instruct
7B Think: … |
@ollama |
Company |
Original |
2025-12-16 |
19,743 |
363 |
39 |
3 |
2 |
81 |
| .@MistralAI's Devstral 2 family of models are now available in Ollama.
24B:
ollama run devstral-small-2
123B:
oll… |
@ollama |
Company |
Original |
2025-12-12 |
27,633 |
431 |
52 |
6 |
5 |
85 |
| .@essential_ai's rnj-1 model is now on Ollama!
ollama run rnj-1
8B parameter, open-weight dense model trained from s… |
@ollama |
Company |
Original |
2025-12-09 |
31,731 |
245 |
33 |
9 |
4 |
67 |
| ollama run deepseek-v3.2:cloud
DeepSeek v3.2 is now on Ollama's cloud!
DeepSeek v3.2 on Ollama's cloud can have thin… |
@ollama |
Company |
Original |
2025-12-09 |
23,707 |
421 |
48 |
14 |
5 |
58 |
| Qwen 3 Next is now on Ollama!
ollama run qwen3-next https://t.co/W9kAxo57qA |
@ollama |
Company |
Original |
2025-12-09 |
18,528 |
320 |
33 |
10 |
1 |
44 |
| Run Mistral Large 3 on Ollama's cloud:
ollama run mistral-large-3:675b-cloud |
@ollama |
Company |
Quote |
2025-12-04 |
9,066 |
107 |
8 |
3 |
0 |
21 |
| Ministral 3 is now also available on Ollama's cloud:
14B:
ollama run ministral-3:14b-cloud
8B:
ollama run ministral-3… |
@ollama |
Company |
Quote |
2025-12-03 |
14,837 |
173 |
25 |
2 |
1 |
26 |
| Mistral 3 is now available on Ollama v0.13.1 (currently in pre-release on GitHub).
14B:
ollama run ministral-3:14b
… |
@ollama |
Company |
Quote |
2025-12-02 |
84,341 |
827 |
110 |
26 |
17 |
182 |
| Uh oh. 🍔 https://t.co/d6FpQVdvqm |
@ollama |
Company |
Quote |
2025-11-22 |
26,071 |
151 |
9 |
2 |
0 |
6 |
| Microsoft added support for @ollama to PowerToys 0.96
Now you can use Ollama for advanced clipboard management. Transf… |
@ollama |
Company |
Original |
2025-11-21 |
18,827 |
273 |
26 |
4 |
1 |
106 |
| Ollama v0.13 now supports DeepSeek-OCR!
ollama run deepseek-ocr
Try it with Ollama's CLI or directly use the model… |
@ollama |
Company |
Original |
2025-11-20 |
41,184 |
771 |
117 |
17 |
4 |
333 |
| ollama run vanta-research/scout-4b |
@ollama |
Company |
Quote |
2025-11-20 |
16,079 |
97 |
7 |
3 |
0 |
51 |
| New open-weight LLM by Deep Cogito!
Locally (671B):
ollama run cogito-2.1
Ollama's Cloud:
ollama run cogito-2.1:6… |
@ollama |
Company |
Quote |
2025-11-19 |
32,363 |
178 |
30 |
5 |
1 |
46 |
| Gemini 3 pro now updated on free tier, pro tier and max tier!
ollama run gemini-3-pro-preview
Now back to more open … |
@ollama |
Company |
Quote |
2025-11-18 |
55,039 |
379 |
34 |
5 |
7 |
76 |
| ollama run gemini-3-pro-preview
🧠 State-of-the-art reasoning
🖼️ Deep multimodal understanding
💻 Powerful vibe codin… |
@ollama |
Company |
Original |
2025-11-18 |
192,281 |
720 |
66 |
22 |
11 |
151 |
