| Community feedback told us to update our PyTorch templates.
The new lineup covers PyTorch 2.6, 2.7, 2.8, 2.9, 2.12, an… |
@runpod |
Company |
Original |
2026-10-24 |
301 |
2 |
0 |
0 |
0 |
0 |
| What does AI compute look like right now?
We used aggregated trends from across the platform to find out.
Next week, … |
@runpod |
Company |
Original |
2026-10-23 |
312 |
4 |
0 |
2 |
0 |
0 |
| Day 1 at AGNTCon + MCPCon ✌️
We’re here again today. Come say hi! https://t.co/qXqOED1Odx |
@runpod |
Company |
Original |
2026-10-23 |
573 |
6 |
0 |
0 |
0 |
0 |
| GLM-5.3 is live on our public endpoints.
Built by @Zai_org, it's especially good at code generation and handling mult… |
@runpod |
Company |
Original |
2026-10-23 |
296 |
0 |
0 |
0 |
0 |
0 |
| Three of our GPU fleets are on track to more than double by December.
So if you've been sizing workloads around what'… |
@runpod |
Company |
Original |
2026-10-22 |
354 |
3 |
0 |
1 |
0 |
0 |
| We've met a lot of builders at the @PyTorch Conference so far. Thanks to everyone who stopped by.
We'll still be ther… |
@runpod |
Company |
Original |
2026-10-21 |
685 |
4 |
1 |
0 |
0 |
0 |
| Architectural renders in minutes, not days.
Gendo moved to Runpod Serverless in two days, saved 100+ hours on DevOps,… |
@runpod |
Company |
Original |
2026-10-21 |
402 |
1 |
0 |
0 |
0 |
0 |
| Cal Hacks 13.0 is taking place this week.
A 36-hour hackathon at one of the best venues of SF: the Palace of Fine Art… |
@runpod |
Company |
Original |
2026-10-20 |
397 |
3 |
0 |
0 |
0 |
0 |
| PyTorch Conference is happening this week in San Jose and we’ll be there.
Come say hi if you’re working on training, i… |
@runpod |
Company |
Original |
2026-10-19 |
509 |
5 |
1 |
1 |
0 |
0 |
| If Nix is how you manage your environment, Flash now fits right in.
nix run github:runpod/flash gives you the CLI with… |
@runpod |
Company |
Original |
2026-10-18 |
450 |
2 |
0 |
0 |
0 |
0 |
| @LangChain is the most frequently observed agent framework in Runpod workloads.
The common use cases are practical: re… |
@runpod |
Company |
Original |
2026-10-17 |
523 |
1 |
0 |
0 |
0 |
0 |
| Happy to be partnering with you on this one, @ComfyUI
$25K in prizes and some RTX 5090s up for grabs.
Check out the… |
@runpod |
Company |
Quote |
2026-10-16 |
2,572 |
23 |
3 |
6 |
0 |
5 |
| Q3 on Runpod took more of the work of scaling off your plate.
Batch inference on Serverless, storage that isn’t pinned… |
@runpod |
Company |
Original |
2026-10-15 |
344 |
2 |
0 |
0 |
0 |
0 |
| Open Source Films is making a feature film with an entirely open-source, AI-assisted VFX pipeline.
The entire pipelin… |
@runpod |
Company |
Original |
2026-10-15 |
653 |
9 |
2 |
1 |
0 |
7 |
| Whoa now... we just made @LinkedIn's Top Startups 2026 list.
This isn't one you can apply for. We were one of 50 compa… |
@runpod |
Company |
Original |
2026-10-14 |
522 |
6 |
1 |
4 |
0 |
1 |
| Startups usually compare GPU clusters on the per-GPU hourly rate.
But a large part of the bill comes from somewhere e… |
@runpod |
Company |
Original |
2026-10-14 |
293 |
5 |
0 |
0 |
0 |
1 |
| AI infrastructure doesn’t scale cleanly.
When you size to peak, you pay for idle GPUs throughout the quarter. Size to … |
@runpod |
Company |
Original |
2026-10-13 |
402 |
5 |
0 |
1 |
0 |
0 |
| The platform for your AI.
Now on Caltrain, too. https://t.co/ii2lWLhOLP |
@runpod |
Company |
Original |
2026-10-13 |
306 |
1 |
0 |
0 |
0 |
1 |
| Fine-tuning is excellent at style, but it’s unreliable for facts.
Which is why the best results come from combining t… |
@runpod |
Company |
Original |
2026-10-12 |
308 |
1 |
0 |
1 |
0 |
0 |
| DeepSeek’s share of OpenRouter token volume doubled from 9% in January to 18% in June 2026.
That measures combined inp… |
@runpod |
Company |
Original |
2026-10-10 |
430 |
7 |
0 |
1 |
0 |
0 |
| We have a new community template on Runpod: Decision 2.0 for Serverless.
You just send a question and get back a prob… |
@runpod |
Company |
Original |
2026-10-09 |
480 |
12 |
1 |
1 |
0 |
0 |
| Migrating an AI pipeline usually means rewriting it. But for a codebase that’s been running since 2021, that’s not an o… |
@runpod |
Company |
Original |
2026-10-09 |
270 |
1 |
0 |
0 |
0 |
0 |
| @LangChain is the most frequently observed agent framework in Runpod workloads.
The common use cases are practical: re… |
@runpod |
Company |
Original |
2026-10-08 |
282 |
0 |
0 |
0 |
0 |
0 |
| Global Volumes are in beta for Runpod Serverless.
Store model weights once, and your workers can start in any data ce… |
@runpod |
Company |
Original |
2026-10-08 |
246 |
0 |
0 |
0 |
0 |
0 |
| Hybrid stacks are common on Runpod:
80% of Pods that reference a frontier model also run open weights or a local servi… |
@runpod |
Company |
Original |
2026-10-08 |
241 |
0 |
0 |
0 |
0 |
0 |
| Fast Company just named us one of the Next Big Things in Tech for 2026.
Alongside some really impressive teams working… |
@runpod |
Company |
Original |
2026-10-07 |
276 |
0 |
0 |
0 |
0 |
0 |
| What does it take to go from a Python function to a GPU endpoint?
Join us on Discord this Friday (October 9) at 1:00 P… |
@runpod |
Company |
Original |
2026-10-07 |
260 |
1 |
1 |
0 |
0 |
0 |
| Architects used to wait three months for a client to approve a render.
Rendair is helping them bring that down to one… |
@runpod |
Company |
Original |
2026-10-06 |
280 |
0 |
0 |
0 |
0 |
0 |
| Qwen models now run on 74.2% of Runpod text endpoints.
Qwen3.x alone rose from 24.3% to 50.4% between November 2025 an… |
@runpod |
Company |
Original |
2026-10-05 |
342 |
4 |
0 |
3 |
0 |
1 |
| “With Runpod, we can choose the right card for the job.”
That’s why Nodalview only moved their inference to Runpod. Th… |
@runpod |
Company |
Original |
2026-10-04 |
474 |
8 |
0 |
5 |
0 |
2 |
| There’s been a lot of chatter about OpenJev over the past couple of weeks.
So we wanted to make it easy for you to try… |
@runpod |
Company |
Original |
2026-10-03 |
343 |
0 |
0 |
0 |
0 |
2 |
| LTX grew from 1.7% to 25.4% of Runpod video endpoints in eight months.
That's a gain of 23.7 percentage points and a n… |
@runpod |
Company |
Original |
2026-10-02 |
322 |
3 |
0 |
0 |
0 |
1 |
| Scatter Lab's Zeta app lets people become the main character in a story and talk to AI characters like they're real.
… |
@runpod |
Company |
Original |
2026-10-01 |
322 |
1 |
0 |
2 |
0 |
1 |
| RT @ComfyUI: Comfy API is live
Point it at a workflow JSON and it handles the rest:
→ Resolves your custom nodes, mod… |
@runpod |
Company |
Repost |
2026-09-30 |
42 |
0 |
212 |
0 |
0 |
0 |
| What can 1.2 million developers tell you about where AI is actually going?
Our own Charlotte Daniels dug into the data… |
@runpod |
Company |
Original |
2026-09-30 |
290 |
0 |
0 |
0 |
0 |
0 |
| Congrats to the team that created Peel, which won the 1st-place grand prize at HackMIT out of hundreds of projects!
Th… |
@runpod |
Company |
Original |
2026-09-30 |
318 |
4 |
0 |
0 |
0 |
0 |
| The 2026 State of AI Compute Fall report is live.
We analyzed what 1M+ Runpod developers ran: model precision, open + … |
@runpod |
Company |
Original |
2026-09-29 |
298 |
1 |
0 |
0 |
0 |
0 |
| The 2026 State of AI Compute Fall report is live.
We analyzed what 1M+ Runpod developers ran: model precision, open + … |
@runpod |
Company |
Original |
2026-09-29 |
301 |
6 |
0 |
0 |
0 |
0 |
| Jacob Seeger built @facelessvideo as a solo founder, moved his video generation workload onto Runpod Serverless, and cu… |
@runpod |
Company |
Original |
2026-09-28 |
433 |
2 |
0 |
0 |
0 |
3 |
| We brought LEGO to WeAreDevelopers last Thursday, and it turns out everyone's a builder.
Thanks to everyone who joine… |
@runpod |
Company |
Original |
2026-09-27 |
339 |
0 |
0 |
1 |
0 |
0 |
| Just spun up your first Pod and wondering how to get your files onto it?
We just wrote a guide that covers everything… |
@runpod |
Company |
Original |
2026-09-26 |
292 |
0 |
0 |
1 |
0 |
0 |
| Always humbled and excited to see what our customers run on Runpod |
@runpod |
Company |
Quote |
2026-09-24 |
1,858 |
9 |
0 |
1 |
1 |
0 |
| You shouldn’t have to choose between the cloud your dev team already uses and the cloud your company can approve.
That… |
@runpod |
Company |
Original |
2026-09-24 |
313 |
3 |
0 |
1 |
0 |
1 |
| @WeAreDevs World Congress kicks off in San Jose this week, and our team will be there.
On Friday, Jessica Garson Beauc… |
@runpod |
Company |
Original |
2026-09-23 |
283 |
0 |
0 |
0 |
0 |
0 |
| We're going live tomorrow with Greg Wester and Vijay Chauhan.
In 30 minutes, they'll take you through what separates e… |
@runpod |
Company |
Original |
2026-09-23 |
292 |
0 |
0 |
0 |
0 |
0 |
| We’re co-hosting a meetup together with Flox & Apify. Demos, drinks, bites, and LEGO (for all the builders out ther… |
@runpod |
Company |
Original |
2026-09-22 |
285 |
0 |
0 |
0 |
0 |
0 |
| "If you simply drop a cutting-edge LLM into the average corporate data warehouse, it doesn't become a brilliant data an… |
@runpod |
Company |
Original |
2026-09-22 |
617 |
5 |
0 |
1 |
1 |
0 |
| Nearly three years ago, Rendair started with just one serverless endpoint on Runpod.
They now run 22 in production, w… |
@runpod |
Company |
Original |
2026-09-21 |
507 |
10 |
0 |
0 |
0 |
2 |
| We've shipped a lot of new stuff lately, and we want to show you.
On September 24, Greg Wester is walking through the… |
@runpod |
Company |
Original |
2026-09-20 |
394 |
5 |
0 |
1 |
0 |
0 |
| Browser-use agents that read the DOM don't need a vision model at all. Screenshot-based agents need one running for eve… |
@runpod |
Company |
Original |
2026-09-19 |
654 |
9 |
1 |
2 |
0 |
2 |
| Which GPU should you use for embedding workloads?
We benchmarked seven models across 24 GPU types and three serving e… |
@runpod |
Company |
Original |
2026-09-19 |
307 |
3 |
1 |
1 |
0 |
0 |
| Did you know that you can self-host n8n on Runpod?
Our team wrote a guide on how to set it up:
https://t.co/xngZoz6uAW |
@runpod |
Company |
Original |
2026-09-18 |
329 |
3 |
0 |
0 |
0 |
0 |
| We’ll be at @WeAreDevs in San José next week.
And on September 25, our own Jessica Garson Beauchemin will show you wha… |
@runpod |
Company |
Original |
2026-09-18 |
289 |
2 |
1 |
0 |
0 |
0 |
| https://t.co/5LRJ1u8CGb |
@runpod |
Company |
Original |
2026-09-17 |
492 |
7 |
2 |
6 |
0 |
3 |
| You don’t get to plan when a Product Hunt launch goes viral.
But that’s what happened with Coframe when their Living … |
@runpod |
Company |
Original |
2026-09-17 |
251 |
0 |
0 |
0 |
0 |
0 |
| Today we’re launching Global Volumes in beta.
Now you can mount elastic, region-independent storage into a Pod in any … |
@runpod |
Company |
Original |
2026-09-16 |
623 |
12 |
1 |
7 |
0 |
6 |
| RT @jessicagarson: We’ll be at the @runpod booth at @TheLeadDev NYC. Come say hi of you are around! https://t.co/RfA8BO… |
@runpod |
Company |
Repost |
2026-09-16 |
71 |
0 |
1 |
0 |
0 |
0 |
| Asking yourself whether to eat the cost of your Kubernetes GPU stack?
We put together an honest look at what the retro… |
@runpod |
Company |
Original |
2026-09-15 |
806 |
3 |
0 |
2 |
1 |
2 |
| The sales process covers pricing, specs, and roadmap.
Nobody talks about what happens six months in when capacity get… |
@runpod |
Company |
Original |
2026-09-15 |
468 |
3 |
0 |
1 |
0 |
0 |
| Adding GPUs doesn't automatically mean more throughput.
NVLink vs PCIe is a 14x bandwidth gap, and NCCL picking the w… |
@runpod |
Company |
Original |
2026-09-14 |
464 |
4 |
2 |
1 |
0 |
1 |
| Already know a workload can run and need predictable access to the GPUs powering it?
A private GPU pool is often the b… |
@runpod |
Company |
Original |
2026-09-14 |
397 |
6 |
0 |
0 |
0 |
0 |
| Nearly three years in and @Rendair has already generated 13M+ images, 22 production endpoints, and zero migrations with… |
@runpod |
Company |
Original |
2026-09-13 |
476 |
3 |
0 |
1 |
0 |
2 |
| Your MCP server works perfectly until your laptop goes to sleep.
We wrote a guide to hosting it on a cloud pod instea… |
@runpod |
Company |
Original |
2026-09-12 |
354 |
4 |
0 |
2 |
0 |
0 |
| Bad GPUs don’t crash. But they do give you a NaN 40 minutes into a training run and never say a word…
Ten minutes of c… |
@runpod |
Company |
Original |
2026-09-12 |
301 |
5 |
0 |
1 |
0 |
0 |
| Most of what "enterprise-grade" means only shows up after you've signed the contract.
Sign up for our next webinar to… |
@runpod |
Company |
Original |
2026-09-11 |
305 |
3 |
0 |
0 |
0 |
0 |
| You don't need a whole card to run a model that fits in a quarter of one.
RTX PRO 6000 Blackwell MIG partitions are no… |
@runpod |
Company |
Original |
2026-09-10 |
322 |
5 |
0 |
0 |
0 |
0 |
| Since Kimi K3 launched in July, it’s become one of the fastest-growing models we serve through Runpod’s public endpoint… |
@runpod |
Company |
Original |
2026-09-09 |
9,888 |
38 |
5 |
2 |
0 |
7 |
| Qwen3.8-Flash-Next was serving on Runpod Serverless ~11 min after scale-up.
Alibaba’s Qwen4 serving-stack preview: 125… |
@runpod |
Company |
Original |
2026-09-08 |
611 |
7 |
1 |
0 |
0 |
0 |
| One unpaginated MCP tool call killed an entire agent session.
We found it in our own server during an internal audit.… |
@runpod |
Company |
Original |
2026-09-08 |
367 |
1 |
0 |
2 |
0 |
0 |
| Five Qwen generations in 2026. Three have open weights, two don't.
If you just want the answer: Qwen3.6-27B, dense, f… |
@runpod |
Company |
Original |
2026-09-07 |
311 |
0 |
0 |
1 |
0 |
1 |
| If your inference is memory-bound at low batch sizes, speculative decoding can help.
N-gram speculation costs zero ext… |
@runpod |
Company |
Original |
2026-09-06 |
387 |
3 |
0 |
0 |
0 |
1 |
| When your AI product goes viral overnight, you don’t want your infrastructure to hold you back.
Yet, for many startups… |
@runpod |
Company |
Original |
2026-09-06 |
324 |
2 |
0 |
1 |
0 |
0 |
| "Private AI server" means something different to everyone who says it.
We wrote the guide to what each option actuall… |
@runpod |
Company |
Original |
2026-09-05 |
291 |
1 |
0 |
0 |
0 |
1 |
| A year ago, models like Kimi K3 were a 64-GPU conversation. But now, it fits on a single 8xB300 pod.
See our walkthrou… |
@runpod |
Company |
Original |
2026-09-05 |
356 |
1 |
0 |
0 |
1 |
0 |
| Z-Image Turbo generates images in eight steps on as little as 6 GB of VRAM.
At $0.005 per image on the Runpod endpoin… |
@runpod |
Company |
Original |
2026-09-04 |
293 |
2 |
0 |
0 |
0 |
0 |
| Have you seen what @PrunaAI's P-Video-Edit model can do?
Upload a short video, add reference images, describe the edit… |
@runpod |
Company |
Original |
2026-09-04 |
514 |
7 |
0 |
0 |
0 |
2 |
| In 2023, everyone was talking about training. That conversation still matters, but it's not what's eating your week any… |
@runpod |
Company |
Original |
2026-09-03 |
498 |
1 |
0 |
3 |
0 |
0 |
| Looking to bring GPU infrastructure to your customers?
The Runpod Partner Program has six different partner tracks. So… |
@runpod |
Company |
Original |
2026-09-03 |
322 |
1 |
0 |
0 |
0 |
1 |
| RT @jessicagarson: I’ve been hanging out in the expo hall at CloudX 2026/API World/AI Tech World. I’m working the @runp… |
@runpod |
Company |
Repost |
2026-09-03 |
59 |
0 |
1 |
0 |
0 |
0 |
| The GPU you need for fine-tuning depends more on method than model size.
A 70B model needs ~560 GB for full fine-tuni… |
@runpod |
Company |
Original |
2026-09-02 |
297 |
2 |
0 |
0 |
0 |
0 |
| We’re now ISO 27001 certified.
Whether your team evaluates on SOC 2, ISO, or both, we have the documentation ready fo… |
@runpod |
Company |
Original |
2026-09-02 |
374 |
5 |
0 |
0 |
0 |
0 |
| The longer the video clip, the more expensive it gets. Right?
FramePack is actually proving the opposite. It can gener… |
@runpod |
Company |
Original |
2026-09-01 |
318 |
2 |
0 |
0 |
0 |
0 |
| The decision between RoCE or InfiniBand gets strong opinions. But rarely will you get a specific number.
Our team rec… |
@runpod |
Company |
Original |
2026-09-01 |
306 |
3 |
0 |
0 |
0 |
0 |
| Want to help shape the cloud platform that 1M+ AI developers rely on?
We're hiring across the company and here are som… |
@runpod |
Company |
Original |
2026-08-31 |
615 |
4 |
0 |
1 |
0 |
1 |
| Agents don't load infrastructure the way a single model call does.
They hold state, loop unpredictably, and burst.
O… |
@runpod |
Company |
Original |
2026-08-30 |
605 |
5 |
0 |
1 |
0 |
1 |
| Every LangChain RAG tutorial plugs in OpenAI and calls it done.
That works until you're metered per token, rate-limit… |
@runpod |
Company |
Original |
2026-08-29 |
491 |
5 |
0 |
0 |
0 |
0 |
| Capping AI video at a few seconds because of VRAM limits?
With FramePack, you can generate long clips on a single GPU … |
@runpod |
Company |
Original |
2026-08-28 |
325 |
1 |
0 |
1 |
0 |
1 |
| TOOL used to fly cases of 4090s through airports to run GPU workloads on client sites. Now they run everything on Runpo… |
@runpod |
Company |
Original |
2026-08-28 |
530 |
10 |
0 |
1 |
0 |
1 |
| We recently changed how Serverless picks a machine for your worker.
And the change makes that setting work harder tha… |
@runpod |
Company |
Original |
2026-08-28 |
611 |
11 |
0 |
1 |
0 |
0 |
| Nobody picks a Python version on purpose anymore.
That works fine. Until it doesn’t. Including for us at Runpod.
So… |
@runpod |
Company |
Original |
2026-08-27 |
515 |
3 |
0 |
0 |
0 |
0 |
| AWS ECR tokens expire every 12 hours.
So running a private ECR image on a Pod meant you'd have to mirror it, make the… |
@runpod |
Company |
Original |
2026-08-27 |
476 |
4 |
0 |
0 |
0 |
0 |
| Need a GPU that doesn't touch another workload other than yours?
There are three options, but each comes with a compl… |
@runpod |
Company |
Original |
2026-08-26 |
346 |
2 |
2 |
0 |
0 |
0 |
| REST API v2 is here.
One consistent surface for the whole platform that both humans and AI agents can use to build. Cr… |
@runpod |
Company |
Original |
2026-08-26 |
525 |
7 |
0 |
0 |
0 |
2 |
| How fast is your serverless cold start? 48% of ours are under 200ms. We benchmarked 10 platforms side by side: Runpod, … |
@runpod |
Company |
Original |
2026-08-25 |
450 |
6 |
0 |
2 |
0 |
0 |
| From September 6-11, we’ll be running a six-day, online hackathon for builders. And we’d like to invite you to join us!… |
@runpod |
Company |
Original |
2026-08-25 |
454 |
5 |
1 |
0 |
0 |
6 |
| South Korea has one of the most active AI builder communities we've seen.
Our APAC team got to experience that firstha… |
@runpod |
Company |
Original |
2026-08-25 |
422 |
4 |
0 |
1 |
0 |
1 |
| RTX A4500 is available on Runpod with no waitlist. Spin one up in seconds and only pay for what you use.
Get started h… |
@runpod |
Company |
Original |
2026-08-24 |
334 |
3 |
0 |
0 |
0 |
1 |
| Tired of running your own GPU provider evaluation?
We did it. 12 platforms, ranked across hardware, pricing, scalabil… |
@runpod |
Company |
Original |
2026-08-24 |
273 |
1 |
0 |
0 |
0 |
0 |
| Stop a Pod, and anything sitting on the container disk goes with it.
Your pip installs, your HuggingFace cache, check… |
@runpod |
Company |
Original |
2026-08-24 |
364 |
2 |
0 |
1 |
0 |
1 |
| We loved seeing all the projects at the @AITinkerers meetup in NYC last week.
Nothing like a room full of builders sho… |
@runpod |
Company |
Original |
2026-08-23 |
411 |
2 |
0 |
0 |
0 |
0 |
| Capable open-source models are just a download away.
But then the real questions start…
Where does it run?
What does… |
@runpod |
Company |
Original |
2026-08-23 |
476 |
5 |
2 |
0 |
0 |
1 |
| If your model is deployed but your GPU bill keeps climbing, the gap is usually in the config.
Our tuning guide that t… |
@runpod |
Company |
Original |
2026-08-22 |
398 |
3 |
0 |
0 |
0 |
1 |
| ECR access tokens expire every 12 hours.
Until now, that meant mirroring to another registry, going public, or pastin… |
@runpod |
Company |
Original |
2026-08-22 |
384 |
3 |
0 |
0 |
0 |
1 |
| The buy-vs-rent decision usually comes down to one thing:
How many hours a week your GPU is actually working.
We br… |
@runpod |
Company |
Original |
2026-08-21 |
294 |
0 |
0 |
0 |
0 |
0 |
| Since @Alibaba_Qwen 3.8-27B shipped last Thursday, we've seen deployments converge around a 48GB MIG slice of @nvidia R… |
@runpod |
Company |
Original |
2026-08-21 |
560 |
6 |
0 |
0 |
0 |
0 |
| Great walkthrough on using MiniMax-H3-Realism-People LoRA for realistic portraits by @ai_hakase_.
And if your local ma… |
@runpod |
Company |
Quote |
2026-08-21 |
536 |
1 |
0 |
1 |
0 |
2 |
| https://t.co/v8Rs75VfNp |
@runpod |
Company |
Original |
2026-08-20 |
343 |
0 |
0 |
1 |
0 |
0 |
| Heads up if you're evaluating A100s:
They often come in packs of eight.
That's why we put together a pricing compari… |
@runpod |
Company |
Original |
2026-08-19 |
271 |
0 |
0 |
1 |
0 |
0 |
| Ever tried explaining your GPU bill at the end of the month and realized nobody tagged anything?
That's why we built … |
@runpod |
Company |
Original |
2026-08-19 |
306 |
0 |
0 |
1 |
0 |
0 |
| What does production AI look like at scale? For @HelloCivitai, it's 868K+ LoRAs trained per month on 500+ GPUs.
2.6 m… |
@runpod |
Company |
Original |
2026-08-18 |
514 |
4 |
0 |
1 |
0 |
0 |
| Missed our webinar on the four decisions that make or break inference at scale?
The session with Greg Wester & Bro… |
@runpod |
Company |
Original |
2026-08-17 |
456 |
1 |
0 |
1 |
0 |
0 |
| @MiniMax_AI M3 is a lot of model. But there are a couple of things to keep in mind before building.
Here's what it act… |
@runpod |
Company |
Original |
2026-08-16 |
454 |
2 |
0 |
0 |
0 |
0 |
| Thank you to everyone who stopped by our @Ai4Conferences booth and went on camera with us.
Same time next year? https… |
@runpod |
Company |
Original |
2026-08-15 |
762 |
4 |
0 |
0 |
0 |
0 |
| MiniMax M3: 428B params, 23B active per token, native video input, 1M context window. Open weights. We ran it and wrote… |
@runpod |
Company |
Original |
2026-08-14 |
1,397 |
8 |
1 |
0 |
0 |
4 |
| The weights are out & LTX-2.5 is worth your attention.
The quality gap that used to justify slower models has substant… |
@runpod |
Company |
Original |
2026-08-14 |
421 |
1 |
0 |
1 |
0 |
0 |
| The weights from @ltx_io are out & LTX-2.5 is worth your attention.
The quality gap that used to justify slower models… |
@runpod |
Company |
Original |
2026-08-14 |
405 |
1 |
0 |
0 |
0 |
0 |
| Real-time or batch? One GPU or four?
We'll be going through the decisions that matter with Greg Wester this Thursday.… |
@runpod |
Company |
Original |
2026-08-11 |
393 |
4 |
0 |
1 |
0 |
0 |
| What would you build if your image generation pipeline wasn't bottlenecked by local hardware?
ComfyUI + Flux on a clo… |
@runpod |
Company |
Original |
2026-08-11 |
412 |
2 |
0 |
0 |
0 |
0 |
| Refreshing the deploy page, waiting for a GPU to free up; we've all done it.
Deploy When Available takes that off your… |
@runpod |
Company |
Original |
2026-08-11 |
418 |
3 |
0 |
0 |
0 |
1 |
| Congratulations to the @transformerlab team on launching Primus today.
It's hard not to be excited about what you're … |
@runpod |
Company |
Quote |
2026-08-10 |
657 |
8 |
0 |
0 |
0 |
1 |
| Have you run the cost math on your inference stack lately?
The gap between frontier API pricing and self-hosted vLLM … |
@runpod |
Company |
Original |
2026-08-07 |
480 |
3 |
1 |
0 |
0 |
0 |
| Our own Greg Wester took the stage at @Ai4Conferences this week for a panel on scaling compute for the AI enterprise.
… |
@runpod |
Company |
Original |
2026-08-06 |
493 |
3 |
0 |
0 |
0 |
1 |
| What are the architectural decisions that make or break production inference at scale?
Tomorrow we're covering the fo… |
@runpod |
Company |
Original |
2026-08-06 |
679 |
2 |
0 |
0 |
0 |
0 |
| Day 2 at @Ai4Conferences, and someone spent 25 minutes on her feet and built our GPU out of LEGO!
Definitely faster th… |
@runpod |
Company |
Original |
2026-08-06 |
726 |
7 |
0 |
1 |
0 |
0 |
| Your models run. You rest.
If you're at @Ai4Conferences in Las Vegas this week, come check out our relaxation station.… |
@runpod |
Company |
Original |
2026-08-05 |
406 |
2 |
0 |
0 |
0 |
0 |
| Wan 2.2 is the most capable open-source video model out right now.
We wrote the guide to running it on Runpod with Co… |
@runpod |
Company |
Original |
2026-08-04 |
492 |
4 |
0 |
1 |
0 |
5 |
| The weights for Kimi K3 have been released!
And we've got a Public Endpoint where you can get started!
If you build a… |
@runpod |
Company |
Original |
2026-08-04 |
906 |
8 |
1 |
0 |
0 |
1 |
| Go is core to how we build Runpod, so the @GopherCon conference feels personal.
Come find us if you're there between … |
@runpod |
Company |
Original |
2026-08-01 |
449 |
2 |
0 |
0 |
0 |
0 |
| Every big company was once a small team hoping it would work.
Some of the ones that made it run their AI on Runpod. Op… |
@runpod |
Company |
Original |
2026-07-31 |
514 |
7 |
0 |
3 |
0 |
1 |
| Kimi K3 is open. If you're already calling the OpenAI SDK, you can reach it on Runpod by changing one line: base_url="h… |
@runpod |
Company |
Original |
2026-07-27 |
420 |
7 |
1 |
0 |
0 |
2 |
| Your application database knows what is. It doesn't know what was.
Our team published how we replaced polling with cha… |
@runpod |
Company |
Original |
2026-07-26 |
819 |
6 |
0 |
1 |
0 |
0 |
| Between traffic spikes, your GPUs sit idle, and the bill keeps climbing.
@KRNL_xyz felt it too, then cut costs 65% b… |
@runpod |
Company |
Original |
2026-07-23 |
331 |
3 |
1 |
0 |
0 |
0 |
| The Runpod MCP server is live.
Use it to work with any MCP client and get ~50 tools for managing your full Runpod inf… |
@runpod |
Company |
Original |
2026-07-23 |
359 |
2 |
0 |
0 |
0 |
1 |
| The serverless tradeoff everyone hits: scale to zero and eat 30-second cold starts, or keep a warm worker running and e… |
@runpod |
Company |
Original |
2026-07-20 |
412 |
9 |
0 |
1 |
0 |
1 |
| At some point, an inference workload outgrows a single cloud provider.
Scatter Lab rearchitected around multi-region … |
@runpod |
Company |
Original |
2026-07-17 |
409 |
7 |
0 |
0 |
0 |
1 |
| Zhen Lu joined @allisonsummers on the Disruptive CEO Nation podcast.
Tailored AI models, cutting compute waste, and b… |
@runpod |
Company |
Original |
2026-07-16 |
1,142 |
4 |
0 |
0 |
0 |
0 |
| "They were nimble. They were fast. We could tell them what we wanted, and they did it."
@DeepCogito co-founder Dhruv M… |
@runpod |
Company |
Original |
2026-07-15 |
372 |
5 |
0 |
0 |
0 |
0 |
| Your agent works great in dev. Then production hits and your costs look like a heart monitor.
Turns out there are fiv… |
@runpod |
Company |
Original |
2026-07-10 |
383 |
2 |
0 |
1 |
0 |
0 |
| Day 2 at @ ICML, Seoul - From the crowd to the console.
Come say hi today! We love to hear what you're building! http… |
@runpod |
Company |
Original |
2026-07-09 |
468 |
2 |
0 |
1 |
0 |
2 |
| "Which inference engine should we use, vLLM or TensorRT-LLM?"
We see this question a lot.
If you're mid-decision, the… |
@runpod |
Company |
Original |
2026-07-05 |
657 |
4 |
1 |
0 |
0 |
0 |
| Deploy When Available is now GA. Queue for any GPU spec, even if it's fully rented out, and we'll deploy your pod the m… |
@runpod |
Company |
Original |
2026-07-03 |
636 |
6 |
0 |
1 |
0 |
1 |
| Flash Hack Day is in the books. 11 teams hacked and demoed live, with real production endpoints, shipped in a day.
Co… |
@runpod |
Company |
Original |
2026-07-02 |
741 |
12 |
0 |
1 |
0 |
1 |
| most inference optimization: here are 20 popular models we made faster
runpod overdrive: what model are you actually r… |
@runpod |
Company |
Original |
2026-07-01 |
634 |
9 |
1 |
1 |
0 |
2 |
| We'll be at the AI Engineer World's Fair this week, June 29 – July 2 in San Francisco.
If you're attending, come find… |
@runpod |
Company |
Original |
2026-06-30 |
718 |
5 |
0 |
2 |
0 |
2 |
| Two days until Flash Hack Day. We've got credits and cash prizes for the top projects, plus a gift for every single per… |
@runpod |
Company |
Original |
2026-06-28 |
654 |
2 |
0 |
0 |
0 |
1 |
| Make Tuesday the best day of your week.
Spend the day building with us on June 30th in SF.
Registration link is belo… |
@runpod |
Company |
Original |
2026-06-26 |
669 |
4 |
0 |
0 |
0 |
1 |
| We just closed a $100M Series A led by @SummitPartners. 🎉
1M+ developers. $22M raised to get here. Almost entirely wo… |
@runpod |
Company |
Original |
2026-06-24 |
2,512 |
15 |
1 |
4 |
4 |
3 |
| Join us for our first Flash hackathon!
June 30, SF. Remote submissions welcome.
https://t.co/HqXAxtZNud https://t.co… |
@runpod |
Company |
Original |
2026-06-22 |
2,857 |
12 |
1 |
5 |
0 |
2 |
| We had a great time at the @databricks Data+AI Summit this week.
Always great to see so many builders who are shippin… |
@runpod |
Company |
Original |
2026-06-20 |
672 |
6 |
0 |
0 |
0 |
0 |
| Join us June 25 for a live demo of what's new in Runpod Serverless — hot starts, batch inference, and a cold-to-running… |
@runpod |
Company |
Original |
2026-06-17 |
779 |
2 |
0 |
1 |
0 |
0 |
| More than half of all internet traffic is now AI agents.
Behind every one of those requests is an inference call that… |
@runpod |
Company |
Original |
2026-06-17 |
372 |
3 |
0 |
0 |
0 |
0 |
| Come build with us during our Flash Hack Day in SF on June 30.
Expect a full-day hackathon where you ship real projec… |
@runpod |
Company |
Original |
2026-06-16 |
363 |
4 |
0 |
0 |
0 |
0 |
| Agents have overtaken humans in internet traffic.
And behind every agent is an inference call that needs to be fast, … |
@runpod |
Company |
Original |
2026-06-15 |
429 |
3 |
0 |
0 |
0 |
0 |
| Getting GPUs right now is already hard.
Once you finally have them, you're staring down node networking, cross-machine… |
@runpod |
Company |
Original |
2026-06-11 |
368 |
3 |
0 |
0 |
0 |
0 |
| Runpod is now in the @thoughtworks Technology Radar (Vol. 34).
Worth exploring for teams that need flexible, cost-eff… |
@runpod |
Company |
Original |
2026-06-11 |
264 |
3 |
1 |
1 |
0 |
1 |
| "We scaled our workloads 10x without worrying about GPU shortages or excessive costs."
That's coming from Segmind, a G… |
@runpod |
Company |
Original |
2026-06-05 |
1,527 |
3 |
0 |
0 |
1 |
1 |
| The bottleneck isn't GPUs anymore.
It's the three to five clouds most AI teams stitch together to get a model to prod… |
@runpod |
Company |
Original |
2026-06-03 |
611 |
4 |
1 |
1 |
1 |
1 |
| 👏👏Congrats to the @MeckaAI team on their Series A. Great to see what they're building on Runpod. |
@runpod |
Company |
Quote |
2026-06-01 |
912 |
6 |
0 |
0 |
0 |
0 |
| "The AI market looks nothing like the narrative."
Our CTO, Brennen Smith, went on TFiR to talk about what we're actual… |
@runpod |
Company |
Original |
2026-06-01 |
547 |
5 |
1 |
1 |
1 |
1 |
| We just launched Multi-Instance GPU (MIG) on Runpod Serverless.
It partitions the RTX 6000 Pro into isolated 24 GB in… |
@runpod |
Company |
Original |
2026-05-29 |
744 |
10 |
1 |
2 |
1 |
0 |
| Runpod Flash is GA ⚡️
Flash is a Python SDK that lets you define infrastructure and deploy AI workloads directly from… |
@runpod |
Company |
Original |
2026-04-30 |
5,436 |
10 |
2 |
2 |
4 |
11 |
| Runpod just shipped Cost Centers. Now you get native spend tracking by team, project, or department, right in the cons… |
@runpod |
Company |
Original |
2026-04-10 |
2,416 |
23 |
6 |
2 |
0 |
2 |
| We put a chat interface in the Runpod console.
23 tools across the full REST API.
If you can do it in the dashboard,… |
@runpod |
Company |
Original |
2026-03-26 |
2,104 |
7 |
1 |
0 |
2 |
4 |
| Runpod is now natively supported in @transformerlab!
Add your API key and get experiment tracking, automatic checkpoin… |
@runpod |
Company |
Quote |
2026-03-26 |
2,131 |
11 |
3 |
0 |
0 |
1 |
| We're the compute partner for OpenAI's Parameter Golf challenge. Need credits? Apply at the link below! |
@runpod |
Company |
Quote |
2026-03-18 |
5,079 |
34 |
5 |
3 |
0 |
8 |
| Runpod is @OpenAI 's infrastructure partner for Parameter Golf, the first challenge in the Model Craft series.
Train t… |
@runpod |
Company |
Original |
2026-03-18 |
23,418 |
57 |
6 |
8 |
4 |
15 |
| The AI market looks nothing like the narrative.
We have the production data to prove it.
The State of AI: what 500K d… |
@runpod |
Company |
Original |
2026-03-12 |
7,357 |
9 |
1 |
4 |
1 |
4 |
| Heading to @QCon London next week!
If you’re working on:
• GPU infrastructure
• inference at scale
• agent systems
• p… |
@runpod |
Company |
Original |
2026-03-11 |
799 |
5 |
0 |
1 |
0 |
0 |
| Introducing Flash.
An open source Python SDK for building cloud-native AI apps. Define your hardware, functions, and d… |
@runpod |
Company |
Original |
2026-03-10 |
8,433 |
26 |
8 |
2 |
2 |
19 |
| $15K in GPU credits. Stanford TreeHacks went by in a flash. More coming soon 👀 https://t.co/LJwTMqW8L1 |
@runpod |
Company |
Original |
2026-03-04 |
1,757 |
11 |
3 |
1 |
0 |
1 |
| Runpod is officially HIPAA and GDPR compliant. Healthcare orgs and EU companies can now train and deploy AI models on o… |
@runpod |
Company |
Original |
2026-02-20 |
1,907 |
7 |
2 |
2 |
1 |
3 |
| Serverless vs. Pods — how to pick the right deployment model for your AI workload 👇
Serverless: Scales to zero, pay-pe… |
@runpod |
Company |
Original |
2026-02-17 |
972 |
4 |
0 |
2 |
0 |
0 |
| Now partnering with @speedrun 🚀
Founders in the program get: → 5K Runpod credits → direct Slack access to our team → … |
@runpod |
Company |
Original |
2026-02-09 |
822 |
10 |
0 |
0 |
1 |
0 |
| We just served our 10 billionth serverless request.
We didn't build this. You did.
Every request = a developer who tr… |
@runpod |
Company |
Original |
2026-02-04 |
908 |
15 |
0 |
2 |
1 |
0 |
| 1/ Big news from Runpod: we've crossed $120M ARR.
500K developers now use the platform to build and run AI systems at … |
@runpod |
Company |
Original |
2026-01-21 |
921 |
7 |
0 |
2 |
0 |
0 |
| 1/ Big news from Runpod: we've crossed $120M ARR.
500K developers now use the platform to build and run AI systems at … |
@runpod |
Company |
Original |
2026-01-20 |
1,191 |
10 |
0 |
1 |
1 |
2 |
| One-click rollbacks for Runpod Serverless endpoints
Broke prod → rollback to previous build instantly
No git reverts,… |
@runpod |
Company |
Original |
2026-01-16 |
503 |
3 |
1 |
0 |
0 |
0 |
| 2026 predictions:
AI agents become default across SaaS, expectations shift from “chat” to autonomous task execution. … |
@runpod |
Company |
Quote |
2026-01-09 |
650 |
5 |
2 |
0 |
0 |
1 |
| Free credits for the first 200! |
@runpod |
Company |
Quote |
2025-12-24 |
3,953 |
14 |
4 |
5 |
1 |
5 |
| Build with us this holiday season! 🎁❄️⛄ |
@runpod |
Company |
Quote |
2025-12-24 |
901 |
5 |
0 |
1 |
0 |
0 |
| Cached models are now GA for Runpod Serverless endpoints.
Cached models unlock:
⚡Faster cold starts (when the model is… |
@runpod |
Company |
Original |
2025-12-17 |
1,065 |
10 |
0 |
2 |
2 |
1 |
| Try Chatterbox Turbo for free this week →
https://t.co/Zp1vkpH2hx |
@runpod |
Company |
Quote |
2025-12-15 |
887 |
3 |
0 |
0 |
1 |
3 |
| We're @NeurIPSConf!
Find us at Booth 633 for our limited manga stickers https://t.co/y6W8dX3PUV |
@runpod |
Company |
Original |
2025-12-04 |
710 |
5 |
1 |
3 |
0 |
0 |
| The best open-weight LLM by a US company, Cogito v2.1 671B, was trained on Runpod as part of their frontier stack. 🇺🇸🦅🚀… |
@runpod |
Company |
Quote |
2025-11-19 |
3,005 |
12 |
4 |
0 |
0 |
3 |
| 🔊👂 https://t.co/MOB6XQo6un |
@runpod |
Company |
Original |
2025-11-14 |
883 |
6 |
0 |
0 |
0 |
0 |
| As an AI founder, the last thing on your mind should be worrying about compute.
Let us handle that.
Autoscaling?… |
@runpod |
Company |
Original |
2025-11-03 |
923 |
5 |
0 |
1 |
0 |
2 |
| https://t.co/N6MguSmox1 |
@runpod |
Company |
Original |
2025-10-27 |
961 |
5 |
0 |
0 |
1 |
0 |
