Unsloth on X / Twitter

Official accounts (1)

Unsloth AI @UnslothAI · Company Primary

Active Accounts: 1 tracked
Posts YTD: 122 ↑ vs 64 last year
Avg Posts/Month: 10.5 since 2025
Views: 39,781,862 219/220 reported
Likes: 298,184 220/220 reported
Reposts: 40,071 220/220 reported
Replies: 10,345 220/220 reported
Quotes: 6,106 220/220 reported
Bookmarks: 181,418 220/220 reported

Monthly Activity

Account: Start year:

Engagement values are the latest totals observed for each post, grouped by publication month. Provider coverage can vary by metric; unavailable values are shown as --.

Post Details

Search:

Post	Account	Account Type	Post Type	Published	Views	Likes	Reposts	Replies	Quotes	Bookmarks
Qwen3.8-27B Unsloth GGUF is now the #1 most-liked GGUF of all time! The model hit 10M downloads and 3.7K likes in just…	@UnslothAI	Company	Original	2026-09-08	85,709	1,722	125	70	21	488
RT @googledevs: ICYMI, we're celebrating 1 BILLION+ downloads for @googlegemma 💎 How are developers actually using ope…	@UnslothAI	Company	Repost	2026-09-05	1,213	0	15	0	0	0
RT @ZixuanLi_: Local GGUF inference is now up to 3.3× faster at long context lengths	@UnslothAI	Company	Repost	2026-09-04	1,159	0	4	0	0	0
We made GLM-5.3-Flash run 3.3x faster locally! Local GGUF inference is now 1.6–3.4× faster with optimized decoding and…	@UnslothAI	Company	Quote	2026-09-04	213,616	1,454	140	61	31	736
You can now run Unsloth GGUFs locally in one-click via Hermes! ✨ Qwen3.8-27B, Qwen3.8-Flash, DeepSeek-V4-Flash and mor…	@UnslothAI	Company	Quote	2026-09-03	67,100	871	75	26	15	299
Qwen3.8-Flash can now run 1.7× faster locally with MTP!⚡️ GGUFs can reach 170 tokens/s on a RTX PRO 6000. MTP enables…	@UnslothAI	Company	Quote	2026-09-02	107,524	1,181	130	62	16	572
RT @NVIDIARobotics: ⚡ Fine-tune and quantize AI models directly on NVIDIA Jetson. Our new Jetson AI Lab tutorial shows…	@UnslothAI	Company	Repost	2026-08-31	1,179	0	53	0	0	0
RT @UnslothAI: GLM-5.3 can now be run locally! The 2-bit model retains ~81% accuracy after we shrunk it from 1.51TB to…	@UnslothAI	Company	Repost	2026-08-29	--	0	206	0	0	0
GLM-5.3 can now be run locally! The 2-bit model retains ~81% accuracy after we shrunk it from 1.51TB to 239GB (-83% si…	@UnslothAI	Company	Quote	2026-08-28	194,963	1,747	196	90	38	592
GLM-5.3-Flash can now be run locally! ✨ Run 3-bit on 128GB RAM via Unsloth GGUF. GLM-5.3-Flash (ox-alpha) rivals Clau…	@UnslothAI	Company	Quote	2026-08-27	291,137	1,650	200	100	42	672
RT @analogalok: The VRAM barrier is officially dead. I just ran Qwen 3.8 Flash Next (MoE) 125B A6B with a 250,000 con…	@UnslothAI	Company	Repost	2026-08-26	1,170	0	427	0	0	0
RT @Alibaba_Qwen: A high-performance 125B model now running locally on just 75GB RAM! Thank you @UnslothAI for the day-…	@UnslothAI	Company	Repost	2026-08-26	853	0	97	0	0	0
Qwen3.8-Flash can now be run locally! 🔥 The 125B MoE model outperforms Claude-Opus-4.6 (Max). Run on 75GB RAM via Uns…	@UnslothAI	Company	Quote	2026-08-26	923,661	2,448	301	157	98	1,460
You can now fine-tune Qwen3.8-27B for free with our notebook! 🔥 Local training works on 24GB VRAM. Unsloth trains Qwe…	@UnslothAI	Company	Original	2026-08-25	148,993	2,012	240	66	27	1,499
RT @danielhanchen: We did a new Unsloth Desktop release! * Experimental auto compaction for any model * LAN & Remo…	@UnslothAI	Company	Repost	2026-08-20	1,032	0	16	0	0	0
RT @Alibaba_Qwen: Huge thanks to Unsloth for the great work. This is wonderful news for the community! 🥳Qwen3.8-27B, sm…	@UnslothAI	Company	Repost	2026-08-20	830	0	121	0	0	0
We’re releasing new Qwen3.8-27B GGUFs with 10% higher accuracy. Unsloth Dynamic V3 outperforms others by >10% on Di…	@UnslothAI	Company	Quote	2026-08-19	1,039,555	5,123	603	224	155	3,336
Qwen3.8-27B Unsloth GGUF is now the #2 trending model on Hugging Face with 2.7M downloads! 💗 Unsloth also reached #3 t…	@UnslothAI	Company	Original	2026-08-18	125,823	1,459	80	50	13	269
RT @NVIDIARTXSpark: Local AI just got a major upgrade. Fine-tune and run AI models locally with @UnslothAI Desktop, pl…	@UnslothAI	Company	Repost	2026-08-18	1,083	0	22	0	0	0
Qwen3.8-27B GGUF has reached 1,000 likes in less than 24 hours! ❤️ It's now the #3 trending model on Hugging Face with…	@UnslothAI	Company	Original	2026-08-15	53,542	1,477	90	70	10	247
RT @ReyReinoso: Qwen3.8-27B + Unsloth is wow! Feels like having an Opus-level coding agent running fully locally it edi…	@UnslothAI	Company	Repost	2026-08-15	1,297	0	21	0	0	0
Share your results from Qwen3.8-27B! 👇 Here's 4-bit Qwen3.8-27B GGUF generating an interactive volcano simulation with…	@UnslothAI	Company	Quote	2026-08-14	65,288	842	75	45	9	188
RT @Alibaba_Qwen: 27B on 17GB RAM. Are you ready to create something incredible? 😎 Thanks for highlighting it! @Unsloth…	@UnslothAI	Company	Repost	2026-08-14	836	0	408	0	0	0
Qwen3.8-27B can now be run locally! ✨ Run on 17GB RAM via Unsloth Dynamic GGUFs. Qwen3.8-27B is by far the strongest …	@UnslothAI	Company	Quote	2026-08-14	1,279,883	5,199	621	204	176	2,765
You can now fine-tune Meta Muse Glimmer 30B for free! 🔥 Our free notebook also supports GRPO RL training. Unsloth tra…	@UnslothAI	Company	Original	2026-08-13	34,974	633	67	22	8	304
2-bit NVIDIA Nemotron 3.5 Lightning ran tool calls nonstop for 10 minutes on just 22GB of VRAM. 🤯 It cited 80+ website…	@UnslothAI	Company	Quote	2026-08-12	83,040	724	70	25	6	329
Qwen3.8 can now be run locally! 🔥 We shrank Qwen3.8-2.4T-A95B from 4.9TB to 397GB (-91% size) via Dynamic 1-bit by sel…	@UnslothAI	Company	Original	2026-08-12	357,501	3,368	386	173	119	1,109
Introducing Unsloth Desktop 🦥 The first desktop app to run and train models locally. • Open-source. Runs on Mac, Windo…	@UnslothAI	Company	Original	2026-08-11	782,053	4,702	623	268	174	3,266
2-bit Muse Glimmer GGUF managed to call 100+ tools on just 14GB RAM. 🔥 Muse Glimmer did a complete repo bug hunt for 5…	@UnslothAI	Company	Quote	2026-08-10	121,774	1,588	136	52	18	762
Meta releases Muse Glimmer, a new 30B open model that runs on 18GB RAM. Muse Glimmer is Apache 2.0 licensed, supports …	@UnslothAI	Company	Quote	2026-08-10	417,242	2,819	319	92	85	1,069
DeepSeek-V4-Flash can now run 2× faster locally with DSpark! ⚡️ DSpark enables V4-Flash-0731 GGUFs to generate ~1.4–2×…	@UnslothAI	Company	Original	2026-08-06	259,578	2,548	219	85	48	1,163
Qwen3.8-27B is coming! 🔥 Will run locally on 17GB RAM/VRAM setups.	@UnslothAI	Company	Quote	2026-08-03	989,936	7,778	594	268	192	1,883
DeepSeek V4 Flash 0731 can now be run locally! 🐳 Run DeepSeek V4 Flash lossless 4-bit on 168GB RAM and 3-bit on 110GB …	@UnslothAI	Company	Quote	2026-07-31	690,597	3,629	454	154	111	1,202
You can now run Inkling-Small, a new 276B model by Thinking Machines. Inkling-Small is the strongest open model for it…	@UnslothAI	Company	Quote	2026-07-30	105,906	839	98	43	14	402
We compared 1-bit Kimi K3 to Claude Opus 5 and GPT 5.6. We gave 4 models the same prompt: Create a glass aquarium whos…	@UnslothAI	Company	Quote	2026-07-29	414,179	2,086	190	98	41	829
Kimi K3 can now be run locally! ✨ The 1-bit model retains ~78.9% accuracy after we shrunk it from 1.56TB to 594GB (-62…	@UnslothAI	Company	Quote	2026-07-29	2,609,036	11,875	1,555	491	448	6,495
We signed the Open Weights letter because we believe the future of AI should be shaped by everyone, not controlled by a…	@UnslothAI	Company	Quote	2026-07-27	76,080	1,565	115	48	17	98
Introducing Unsloth for AMD 🚀 You can now train & run LLMs on your AMD hardware • We collaborated with AMD to enable y…	@UnslothAI	Company	Original	2026-07-20	369,955	2,285	330	117	81	759
Gemma 4 is now faster and much more accurate! 🚀 Google made huge improvements to tool-calling and chat accuracy, relia…	@UnslothAI	Company	Quote	2026-07-17	267,986	1,993	246	64	23	1,057
You can now run Thinking Machines Inkling! Inkling is a 975B open model with image, audio and 1M context support. We …	@UnslothAI	Company	Quote	2026-07-15	101,813	672	89	29	13	280
We’re releasing Gemma 4 NVFP4 quants that run 1.5× faster on your GPU. Gemma-4-12B NVFP4 works on 11GB VRAM. 26B-A4B h…	@UnslothAI	Company	Original	2026-07-14	136,716	1,347	159	62	35	833
We’re releasing new Qwen3.6 quants that run 2.5× faster on your GPU. Qwen3.6-27B NVFP4 runs on 24GB VRAM. 35B-A3B can …	@UnslothAI	Company	Original	2026-07-10	350,277	2,790	351	169	80	1,930
DeepSeek-V4 can now run locally with Unsloth GGUFs! 🐳 Run lossless DeepSeek-V4-Flash on 168GB RAM. 3-bit works on 110G…	@UnslothAI	Company	Original	2026-07-07	97,093	925	113	46	18	351
What’s your go-to local model right now?	@UnslothAI	Company	Original	2026-06-25	114,560	589	19	318	14	207
1-bit GLM-5.2 GGUF vs. Claude 4.8 Opus vs. GPT-5.5 We gave 3 models the same prompt and compared one-shot outputs. Th…	@UnslothAI	Company	Quote	2026-06-23	1,542,322	3,565	406	173	134	2,219
GLM-5.2 can now be run locally!🔥 The 2-bit model retains ~82% accuracy after we shrunk it from 1.51TB to 238GB (-84% s…	@UnslothAI	Company	Quote	2026-06-18	1,895,258	7,326	863	272	275	4,459
You can now run Kimi K2.7 Code locally! 🌘 We shrank the 1T model to 325GB (-48%) via Dynamic 2-bit where important lay…	@UnslothAI	Company	Quote	2026-06-15	1,437,286	2,878	296	168	185	1,498
MiniMax M3 can now be run locally!🔥 MiniMax-M3 is a new 428B (23B active) open model with 1M context that performs on …	@UnslothAI	Company	Quote	2026-06-12	192,341	793	96	60	26	348
DiffusionGemma can now run at 2000+ tokens/sec! ⚡ We made local DiffusionGemma inference 1.8× faster. Run it on 18GB …	@UnslothAI	Company	Quote	2026-06-12	180,297	1,714	182	60	46	1,113
Gemma 4 now runs 2x faster with MTP GGUFs! Run locally on just 6GB RAM. ⚡️ MTP enables Google Gemma 4 run ~1.4–2.2× fa…	@UnslothAI	Company	Original	2026-06-11	222,100	2,147	255	62	34	1,665
Google releases DiffusionGemma.✨ The new 26B-A4B diffusion text model runs locally on 18GB RAM. It supports high-speed…	@UnslothAI	Company	Quote	2026-06-10	336,842	1,827	248	64	51	1,000
Google releases Gemma 4 QAT. ✨ You can now run Gemma 4 at 3x less memory with near original performance. Quantization-…	@UnslothAI	Company	Quote	2026-06-05	255,824	2,874	409	91	68	1,891
You can now run NVIDIA Nemotron 3 Ultra, a new 550B open model. Nemotron-3-Ultra-550B-A55B is NVIDIA's largest LLM yet…	@UnslothAI	Company	Quote	2026-06-04	41,469	412	47	23	7	101
2-bit Gemma 4 12B GGUF, only 4.66 GB on disk, managed to cite 15 sites from a single prompt. Try this locally on >6…	@UnslothAI	Company	Quote	2026-06-04	145,099	1,613	190	46	14	1,101
Gemma 4 12B can now run locally on just 8GB RAM via Dynamic GGUFs. Google's new model, Gemma 4 12B Unified supports im…	@UnslothAI	Company	Quote	2026-06-03	357,116	2,799	371	94	53	1,538
Local models are coming to your laptop soon! 🚀 We're excited to partner with @Microsoft to enable millions of develope…	@UnslothAI	Company	Quote	2026-06-02	42,519	537	49	25	15	132
You can now train 120B+ parameter models locally on a laptop! 🔥 We collabed with NVIDIA and Microsoft to bring LLM tra…	@UnslothAI	Company	Quote	2026-06-02	90,707	1,121	103	54	19	175
We made a guide on using MCP with local LLMs. Connect Qwen3.6 and Gemma 4 for controlled access to tools, files, APIs,…	@UnslothAI	Company	Original	2026-06-01	40,250	988	146	18	9	947
You can now run GPT, Claude & other models in Unsloth. Connect + run APIs in a local UI: - Code execution, web sea…	@UnslothAI	Company	Original	2026-05-26	32,586	263	32	17	5	110
4-bit Qwen3.6 MTP GGUF managed to search 70+ sites from a single prompt. Try this locally on 20GB RAM via Unsloth Stud…	@UnslothAI	Company	Original	2026-05-19	72,434	1,000	119	37	9	739
Qwen3.6 now runs 2x faster with MTP GGUFs! Run locally on just 18GB RAM. ⚡️ MTP enables Qwen3.6 to generate ~1.4–2.2× …	@UnslothAI	Company	Original	2026-05-18	143,434	2,458	293	130	46	1,798
We’re excited to share that Unsloth has joined the PyTorch Ecosystem! Unsloth is an open-source project that makes tra…	@UnslothAI	Company	Original	2026-05-11	90,508	1,307	170	40	19	221
We collaborated with NVIDIA to teach you how we made LLM training ~25% faster! 🚀 Learn how 3 optimizations help your h…	@UnslothAI	Company	Original	2026-05-06	61,630	938	158	21	10	639
We made a guide on how to run open LLMs in Claude Code, Codex and OpenClaw. Use Gemma 4 and Qwen3.6 GGUFs for local ag…	@UnslothAI	Company	Original	2026-05-05	93,605	1,312	229	45	17	1,370
Mistral releases Mistral Medium 3.5, a new vision reasoning model. 🔥 Mistral-Medium-3.5-128B offers highly competitive…	@UnslothAI	Company	Original	2026-04-29	61,484	692	99	23	15	196
NVIDIA releases Nemotron-3-Nano-Omni, a new 30B open multimodal MoE model. Nemotron-3-Nano-Omni-30B-A3B is the stronge…	@UnslothAI	Company	Original	2026-04-28	71,621	935	133	44	21	398
Unsloth is now one of the top 10 most followed organizations on Hugging Face. 🤗🦥 Thanks so much for all the support! h…	@UnslothAI	Company	Original	2026-04-27	65,737	926	49	52	8	58
DeepSeek releases DeepSeek-V4. 🐋 - DeepSeek-V4-Pro: 1.6T params - DeepSeek-V4-Flash: 284B params DeepSeek-V4-Pro riva…	@UnslothAI	Company	Quote	2026-04-24	85,430	1,125	132	53	15	187
2-bit Qwen3.6-27B GGUF made 26 tool calls, triaged 15 GitHub issues and fixed, tested + reproed our repo’s 3 latest iss…	@UnslothAI	Company	Original	2026-04-23	78,603	1,413	157	61	24	990
Qwen3.6-27B can now run locally! 💜 Run on 18GB RAM via Unsloth Dynamic GGUFs. Qwen3.6-27B surpasses Qwen3.5-397B-A17B…	@UnslothAI	Company	Quote	2026-04-22	579,631	3,346	404	93	62	1,979
Kimi K2.6 can now run on CPU, GPU and SSD setups! 🔥 We shrank the 1T model to 340GB via Dynamic GGUFs where important …	@UnslothAI	Company	Quote	2026-04-22	221,857	1,789	167	69	34	705
We benchmarked Gemma 4 26B-A4B GGUFs to identify the best performing quants. Unsloth ranks first in ALL 22 of 22 model…	@UnslothAI	Company	Original	2026-04-20	37,891	613	64	16	4	241
We ran Qwen3.6-35-A3B GGUF performance benchmarks to help you choose the best quant. Unsloth ranks first in 21 of 22 m…	@UnslothAI	Company	Original	2026-04-17	74,750	797	76	47	9	328
2-bit Qwen3.6-35B-A3B did a complete repo bug hunt with evidence, repro, fixes, tests and a PR writeup. 🔥 Run it local…	@UnslothAI	Company	Original	2026-04-16	91,225	1,364	156	50	27	946
Qwen3.6-35B-A3B can now be run locally!💜 The model is the strongest mid-sized LLM on nearly all benchmarks. Run on 23…	@UnslothAI	Company	Quote	2026-04-16	140,738	1,637	197	47	25	840
You can now train Gemma 4 with RL in our free notebook! You just need 9GB VRAM to RL Gemma 4 locally! Gemma 4 will le…	@UnslothAI	Company	Original	2026-04-15	66,148	1,382	224	20	12	1,134
MiniMax 2.7 can now be run locally!🔥 MiniMax-M2.7 is a new 230B parameter open model with SOTA on SWE-Pro and Terminal…	@UnslothAI	Company	Quote	2026-04-12	95,508	748	82	41	17	284
Google DeepMind is hosting a Gemma 4 hackathon with a $10,000 Unsloth prize! 🦥 Show off your best fine-tuned Gemma 4 m…	@UnslothAI	Company	Original	2026-04-10	62,036	856	112	27	14	565
You can now fine-tune Gemma 4 31B for free in our notebook! 🚀 Training the 31B parameter model is completely free with…	@UnslothAI	Company	Original	2026-04-09	158,373	1,595	234	30	15	1,430
GLM-5.1 can now be run locally!🔥 GLM-5.1 is a new open model for SOTA agentic coding & chat. We shrank the 744B m…	@UnslothAI	Company	Quote	2026-04-07	373,892	3,076	336	112	76	1,711
You can now fine-tune Gemma 4 with our free notebooks! 🔥 You just need 8GB VRAM to train Gemma 4 locally! Unsloth tra…	@UnslothAI	Company	Original	2026-04-07	242,165	2,422	346	39	28	2,369
You can now train and run 500+ models in our free notebook!✨ GitHub repo: https://t.co/aZWYAtakBP Colab Notebook: http…	@UnslothAI	Company	Original	2026-04-06	43,517	756	126	14	4	608
Gemma 4 E4B (4-bit) completed a full repo audit by executing Bash code and tool calls locally. Runs on just 6GB RAM. h…	@UnslothAI	Company	Original	2026-04-03	150,229	1,096	105	31	18	651
Gemma 4 E4B was able to search and cite 10+ websites, execute code to find the best answer! 🔥 You only need 6GB RAM to…	@UnslothAI	Company	Quote	2026-04-02	102,788	1,095	122	30	11	672
Google releases Gemma 4. ✨ Gemma 4 introduces 4 models: E2B, E4B, 26B-A4B, 31B. The multimodal reasoning models are un…	@UnslothAI	Company	Quote	2026-04-02	243,554	1,138	165	48	26	489
A new way to use Unsloth. Coming soon... https://t.co/l4lVzYU5qi	@UnslothAI	Company	Original	2026-03-31	25,880	554	30	33	6	65
This model has been #1 trending for 3 weeks now. It's Qwen3.5-27B fine-tuned on distilled data from Claude-4.6-Opus (r…	@UnslothAI	Company	Original	2026-03-30	209,103	2,713	220	86	27	2,291
Inference in Unsloth Studio is now ~20% faster. You can also use older pre-downloaded GGUFs from Hugging Face etc. AM…	@UnslothAI	Company	Original	2026-03-27	25,477	443	40	20	7	144
We shipped 50+ updates to Unsloth Studio in just one week! 🚀 - Unsloth Studio now installs in just 2mins - 10x faster …	@UnslothAI	Company	Quote	2026-03-26	26,434	446	58	14	5	153
You don’t need to manually set LLM parameters anymore! llama.cpp uses only the context length + compute your local set…	@UnslothAI	Company	Original	2026-03-25	69,419	744	65	36	11	498
You can now train Qwen3.5 with RL in our free notebook! You just need 8GB VRAM to RL Qwen3.5-2B locally! Qwen3.5 will…	@UnslothAI	Company	Original	2026-03-23	407,975	2,696	393	30	40	2,592
Unsloth Studio now installs in just one line of code! 💚 Available on macOS, Windows and Linux. You can also run @NVID…	@UnslothAI	Company	Quote	2026-03-20	113,333	1,085	140	41	12	783
Qwen3.5-4B searched 20+ websites, cited its sources, and found the best answer! 🔥 Try this locally with just 4GB RAM v…	@UnslothAI	Company	Original	2026-03-19	128,802	2,271	231	64	25	1,850
Introducing Unsloth Studio ✨ A new open-source web UI to train and run LLMs. • Run models locally on Mac, Windows, Lin…	@UnslothAI	Company	Original	2026-03-17	1,738,877	5,587	894	234	197	5,164
We collaborated with @NVIDIA to teach you about Reinforcement Learning and RL environments. Learn: • Why RL environmen…	@UnslothAI	Company	Original	2026-03-13	89,053	1,710	240	26	15	1,672
NVIDIA releases Nemotron-3-Super, a new 120B open hybrid MoE model. Nemotron-3-Super-120B-A12B has a 1M-token context …	@UnslothAI	Company	Original	2026-03-11	82,989	871	123	31	16	357
We created a repo with 250+ notebooks for LLM training. Train locally on your device with 3GB VRAM or free on Colab. …	@UnslothAI	Company	Original	2026-03-10	57,945	1,357	242	28	11	1,249
Learn how to run Qwen3.5 locally using Claude Code. Our guide shows you how to run Qwen3.5 on your server for local ag…	@UnslothAI	Company	Original	2026-03-09	233,331	2,852	348	96	24	3,558
We're releasing our final update to Qwen3.5 GGUFs for improved performance. - Qwen3.5 GGUFs now use our new iMatrix da…	@UnslothAI	Company	Original	2026-03-05	147,836	1,526	187	54	25	804
You can now fine-tune Qwen3.5 with our free notebook! 🔥 You just need 5GB VRAM to train Qwen3.5-2B LoRA locally! Unsl…	@UnslothAI	Company	Original	2026-03-03	379,147	3,293	466	58	31	3,359
Qwen3.5-35B-A3B-GGUF is now the #3 trending model on Hugging Face! Run it locally on 22GB RAM: https://t.co/4lSce5zZbO	@UnslothAI	Company	Original	2026-03-02	28,969	638	47	17	8	173
Qwen releases 4 new Qwen3.5 Small models! Qwen3.5: 0.8B • 2B • 4B • 9B Run Qwen3.5-0.8B, 2B and 4B on your phone. Run…	@UnslothAI	Company	Quote	2026-03-02	193,403	1,532	192	60	29	613
Qwen3.5 is now updated with improved tool-calling & coding performance! Run Qwen3.5-35B-A3B on 22GB RAM. See improveme…	@UnslothAI	Company	Original	2026-02-27	239,460	1,601	189	85	45	933
Run the new Qwen3.5 Medium models! 🔥 - Qwen3.5 35B-A3B (MoE, 24GB RAM) - Qwen3.5 27B (dense, 18GB) - Qwen3.5 122B-A10B…	@UnslothAI	Company	Quote	2026-02-24	111,164	793	95	27	23	300
Qwen3-Coder-Next GGUF is now the most downloaded model on Unsloth! The 80B coding LLM runs on a 36GB RAM Mac / device.…	@UnslothAI	Company	Original	2026-02-23	151,866	945	86	37	13	536
100,000+ models trained with Unsloth have now been open-sourced on Hugging Face! Popular fine-tuned LLMs you can run l…	@UnslothAI	Company	Original	2026-02-20	39,376	672	71	14	9	444
You can now train LLMs in VS Code for free via Colab & Unsloth. We made a guide showing you how to connect any fine-tu…	@UnslothAI	Company	Original	2026-02-18	59,674	1,095	176	32	9	880
You can now run Qwen3.5 locally! 💜 Qwen3.5-397B-A17B is an open MoE vision reasoning LLM for agentic coding & chat. I…	@UnslothAI	Company	Quote	2026-02-16	113,207	823	106	40	16	304
You can now run MiniMax-2.5 locally! 🚀 At 230B parameters, MiniMax-2.5 is the strongest LLM under 700B params, deliver…	@UnslothAI	Company	Quote	2026-02-15	157,127	1,197	130	65	14	845
You can now run GLM-5 locally!🔥 GLM-5 is a new open SOTA agentic coding & chat LLM with 200K context. We shrank the 7…	@UnslothAI	Company	Quote	2026-02-12	233,498	1,809	185	73	46	958
You can now train MoE models 12× faster with 35% less VRAM via our new Triton kernels (no accuracy loss). Train gpt-os…	@UnslothAI	Company	Original	2026-02-10	213,000	1,451	193	50	35	864
We created a tool-calling guide for local LLMs! Learn how to use any open model like Qwen3-Coder-Next and GLM-4.7-Flas…	@UnslothAI	Company	Original	2026-02-05	46,558	1,019	168	22	6	862
Qwen releases Qwen3-Coder-Next. 💜 The new 80B MoE model excels at agentic coding & local use. With 256K context, it de…	@UnslothAI	Company	Quote	2026-02-03	241,345	1,451	179	49	37	621
We successfully trained an LLM without human intervention using Claude Code. We made a guide on how to do this with lo…	@UnslothAI	Company	Original	2026-01-29	136,770	1,991	273	60	13	1,952
You can now run Kimi K2.5 locally! 🔥 We shrank the 1T model to 240GB (-60%) via Dynamic 1-bit. Run at >40 tok/s on 24…	@UnslothAI	Company	Quote	2026-01-28	464,274	2,796	275	87	60	2,170
DeepSeek releases DeepSeek-OCR 2. 🐋 The new 3B model achieves SOTA visual, document and OCR understanding. DeepEncoder…	@UnslothAI	Company	Original	2026-01-27	220,071	3,125	417	50	40	1,948
Unsloth is excited to support @HuggingFace Transformers v5! 🤗🦥 Get all the latest performance improvements in inferenc…	@UnslothAI	Company	Quote	2026-01-26	21,516	314	33	4	1	56
You can now fine-tune embedding models in our free notebook! Improve retrieval and RAG with better semantic search & s…	@UnslothAI	Company	Original	2026-01-22	81,975	693	93	14	5	467
GLM-4.7-Flash GGUFs now produce significantly better outputs, after recent llama.cpp bug fixes. We reconverted and upd…	@UnslothAI	Company	Quote	2026-01-21	152,260	1,365	134	54	24	719
You can now run GLM-4.7-Flash locally on your device!🔥 GLM-4.7-Flash is the best performing 30B model on SWE-Bench and…	@UnslothAI	Company	Quote	2026-01-20	334,845	2,065	259	65	30	1,540
You can now do reinforcement learning training with 7× longer context and no accuracy loss, via our new batching algori…	@UnslothAI	Company	Original	2026-01-15	72,669	543	78	15	7	276
We made a guide on how to run Qwen-Image diffusion models locally! Learn to: • Run Qwen-Image-2512 and Edit-2511 • Use…	@UnslothAI	Company	Original	2026-01-08	31,069	577	90	8	4	428
Qwen releases Qwen-Image-2512, a new SOTA text-to-image model. 💜 It's the top performing open diffusion model on AI Ar…	@UnslothAI	Company	Quote	2025-12-31	120,270	931	133	31	22	562
We just crossed 50,000 stars on GitHub! ⭐🦥 Huge thanks to you, every contributor and our amazing community for all you…	@UnslothAI	Company	Original	2025-12-30	20,534	230	17	13	3	34
Merry Christmas from Unsloth! 🎄🎁 Thank you for all the support this year! We’re excited to keep shipping open-source …	@UnslothAI	Company	Original	2025-12-24	9,479	256	10	14	0	10
You can now fine-tune LLMs with Unsloth then deploy them in @LMStudio! 🦥👾 We made a free notebook to fine-tune Functio…	@UnslothAI	Company	Quote	2025-12-23	60,146	770	102	21	3	574
NVIDIA made a beginner's guide to fine-tuning LLMs with Unsloth! 💚 You'll learn about: - Training methods: LoRA, FFT, …	@UnslothAI	Company	Original	2025-12-22	138,545	1,659	248	28	11	1,442
Google releases FunctionGemma, a new 270M parameter model that runs on just 0.5 GB RAM.✨ Built for tool-calling, run l…	@UnslothAI	Company	Quote	2025-12-18	218,800	2,413	292	45	26	1,890
You can now fine-tune LLMs and deploy them directly on your phone! 🚀 We collabed with PyTorch so you can export and ru…	@UnslothAI	Company	Original	2025-12-17	133,155	2,445	418	61	34	2,020
We teamed up with @NVIDIA and @MatthewBerman to teach you how to do Reinforcement Learning! Learn about: - RL environm…	@UnslothAI	Company	Original	2025-12-16	54,287	903	102	16	7	742
NVIDIA releases Nemotron 3 Nano, a new 30B hybrid reasoning model! 🔥 Nemotron 3 has a 1M context window and the best i…	@UnslothAI	Company	Original	2025-12-15	138,624	1,482	207	52	33	640
You can now train LLMs 3× faster with no accuracy loss, via our new RoPE and MLP kernels. Our Triton kernels plus smar…	@UnslothAI	Company	Original	2025-12-10	641,170	3,297	321	86	62	2,611
Mistral releases Ministral 3, their new reasoning and instruct models! 🔥 Ministral 3 comes in 3B, 8B, and 14B with vis…	@UnslothAI	Company	Quote	2025-12-02	80,723	867	119	17	11	295
You can now do 500K context length fine-tuning with Unsloth! Train gpt-oss-20b to extend its context window to 530K on…	@UnslothAI	Company	Original	2025-12-01	41,623	519	95	14	9	233
You can now run FP8 reinforcement learning on consumer GPUs! Try DeepSeek-R1’s FP8 GRPO at home using only a 5GB GPU. …	@UnslothAI	Company	Original	2025-11-25	145,321	882	128	19	14	519
We made a guide on how to deploy LLMs locally with SGLang! In collab with @lmsysorg, you'll learn to: • Deploy fine-tu…	@UnslothAI	Company	Original	2025-11-21	29,560	430	73	8	6	283
You can now run Unsloth GGUFs locally via Docker! Run LLMs on Mac or Windows with one line of code or no code at all! …	@UnslothAI	Company	Original	2025-11-17	93,689	559	104	10	15	369
You can now run Kimi K2 Thinking locally with our Dynamic 1-bit GGUFs! We shrank the 1T model to 245GB (-62%) & retain…	@UnslothAI	Company	Original	2025-11-08	178,256	1,066	140	41	24	390
You can now fine-tune DeepSeek-OCR with our free notebook! We fine-tuned DeepSeek-OCR, improving its language understa…	@UnslothAI	Company	Original	2025-11-04	80,059	1,543	251	14	7	1,287
You can now run Qwen3-VL locally! 💜 Run the 235B variant for SOTA vision/OCR on 128GB unified memory (dynamic 4-bit). …	@UnslothAI	Company	Original	2025-10-31	92,399	571	90	24	6	280
We teamed up with @NVIDIA to teach you how to fine-tune LLMs on Blackwell & RTX 50 GPUs. Unsloth makes training on Bla…	@UnslothAI	Company	Original	2025-10-27	35,439	623	82	20	0	321
We showcased our one click fine-tuning UI for the first time at the NVIDIA x Mistral AI x Unsloth event at Y Combinator…	@UnslothAI	Company	Quote	2025-10-23	14,230	163	11	6	1	41
You can now quantize LLMs to 4-bit and recover 70% accuracy via Quantization-Aware Training. We teamed up with @PyTorc…	@UnslothAI	Company	Original	2025-10-22	46,528	499	76	19	6	210
We just hit 100 million lifetime downloads on Hugging Face! 🦥🤗 Huge thanks to all of you! The amazing community, model…	@UnslothAI	Company	Original	2025-10-21	32,647	325	27	15	3	26
You can now fine-tune Qwen3-VL (8B) for free with our notebook! Unsloth trains VLMs 1.7x faster with 60% less VRAM and…	@UnslothAI	Company	Original	2025-10-16	107,620	869	128	10	11	655
You can now train models up to 200B parameters locally on NVIDIA DGX Spark with Unsloth! 🦥 Fine-tune, RL & deploy Open…	@UnslothAI	Company	Original	2025-10-15	46,798	809	112	26	9	475
OpenAI shows how gpt-oss can autonomously beat 2048 using reinforcement learning (RL). Training was done locally with …	@UnslothAI	Company	Original	2025-10-09	98,951	1,030	124	18	9	854
We made a free notebook that fine-tunes IBM Granite 4.0 into a powerful support agent! This agent will enable real-tim…	@UnslothAI	Company	Original	2025-10-02	51,184	614	93	11	12	430
IBM releases Granite-4.0, their new series of open models! Run the 'Micro' 3B model on 4GB RAM or 'Small' 32B on 40GB …	@UnslothAI	Company	Original	2025-10-02	42,590	757	114	19	13	355
Unsloth now has a Docker image! 🐳 Train LLMs locally with no setup: just run the image and go. Includes every pre-mad…	@UnslothAI	Company	Original	2025-10-01	94,723	1,337	207	28	12	1,040
LoRA in reinforcement learning (RL) can match full-finetuning performance when done right! 💡 A new @thinkymachines pos…	@UnslothAI	Company	Quote	2025-09-29	72,799	943	141	21	5	457
Join us, @Pytorch and @AMD for a Virtual Hackathon on Oct 18-20. 🔥 Win $10K in prizes by training the best AI agent v…	@UnslothAI	Company	Original	2025-09-27	9,285	95	24	4	3	40
You can now train OpenAI gpt-oss with Reinforcement Learning in our free notebook! This notebook automatically creates…	@UnslothAI	Company	Original	2025-09-26	125,016	1,464	234	23	17	1,154
We're teaming up with @MistralAI and @NVIDIA for an Unsloth event on Tues, Oct 21 at @YCombinator's office! 🦥 Join us…	@UnslothAI	Company	Original	2025-09-22	31,538	159	20	4	4	26
Mistral releases Magistral 1.2, their new reasoning models! 🔥 Magistral-Small-2509 excels at coding + math, and is a m…	@UnslothAI	Company	Original	2025-09-17	50,963	733	108	15	11	313
You can now train Vision LLMs with Reinforcement Learning in our free notebook! Unsloth VLM RL via GRPO: 1.5× faster, …	@UnslothAI	Company	Original	2025-09-16	142,852	1,158	189	15	21	891
Can a 1-bit or 3-bit quantized model outperform GPT-4.1 or Claude-Opus-4? Yes! Today, we're excited to show how LLMs …	@UnslothAI	Company	Original	2025-09-10	165,156	1,321	185	45	27	608
You can now run @xAI Grok 2.5 locally on just 120GB RAM! 🚀 The 270B parameter model runs ~5 t/s on a 128GB Mac with ou…	@UnslothAI	Company	Original	2025-09-08	108,787	894	139	51	37	311
RL used to be memory hungry, but not anymore! Introducing our new kernels & algos that allows faster RL with 50% l…	@UnslothAI	Company	Original	2025-09-04	71,033	552	78	20	10	249
OpenAI gpt-oss with ultra long context is here!🚀 Introducing Unsloth Flex Attention which enables 61K context for gpt-…	@UnslothAI	Company	Original	2025-08-28	141,600	845	136	21	11	387
Run DeepSeek-V3.1 locally on 170GB RAM with Dynamic 1-bit GGUFs!🐋 The 715GB model gets reduced to 170GB (-80% size) by…	@UnslothAI	Company	Original	2025-08-22	59,050	817	118	24	17	346
Learn to fine-tune OpenAI gpt-oss with our new step-by-step guide! Learn about: • Local gpt-oss training + inference F…	@UnslothAI	Company	Original	2025-08-18	41,766	818	134	8	5	722
Google releases Gemma 3 270M, a new model that runs locally on just 0.5 GB RAM.✨ Trained on 6T tokens, it runs fast on…	@UnslothAI	Company	Quote	2025-08-14	154,412	1,685	246	22	27	1,034
You can now fine-tune OpenAI gpt-oss for free with our notebook! Unsloth trains 1.5x faster with -70% VRAM, 10x longer…	@UnslothAI	Company	Original	2025-08-08	196,700	1,394	247	24	22	1,232
You can now run gpt-oss-120b & 20b locally with our GGUFs! 🦥 Run OpenAI's 120b model on 66GB RAM & 20b model on 14GB R…	@UnslothAI	Company	Quote	2025-08-05	94,780	759	145	21	27	331
You can now run the world’s most powerful Western open models locally! The hybrid reasoning 671B model matches o3 &amp…	@UnslothAI	Company	Quote	2025-08-01	40,724	365	50	13	6	130
Qwen3-Coder-Flash is here!✨ The 30B model excels in coding & agentic tasks. Run locally with up to 1M context length. …	@UnslothAI	Company	Quote	2025-07-31	45,103	633	81	16	7	256
The @GoogleDeepMind Gemma 3n Challenge ($150,000 in prizes) ends in 7 days! We've made 2 new fine-tuning Gemma 3n Kagg…	@UnslothAI	Company	Original	2025-07-30	11,193	229	28	0	1	106
Qwen3-30B-A3B-Instruct-2507 is here!✨ The 30B model rivals GPT-4o's performance and runs locally in full precision wit…	@UnslothAI	Company	Quote	2025-07-29	59,072	578	87	17	14	224
You can now run Qwen3-235B-A22B-Thinking-2507 with our Dynamic 2-bit GGUFs! The full 250GB model gets reduced to just …	@UnslothAI	Company	Quote	2025-07-25	20,236	320	43	9	4	105
Run Qwen3-Coder with our Dynamic 2-bit GGUFs! ⭐ We shrank the 480B parameter model to just 182GB (down from 512GB). Al…	@UnslothAI	Company	Quote	2025-07-23	25,914	333	41	3	7	122
You can now run Qwen3-235B-A22B-2507 with our Dynamic 2-bit GGUFs! The full 250GB model gets reduced to just 88GB (-65…	@UnslothAI	Company	Quote	2025-07-22	37,855	548	68	16	10	169
A Complete Guide to Fine-tuning LLMs in 20 mins! Learn to: • Choose the correct model & training method (LoRA, FFT…	@UnslothAI	Company	Original	2025-07-16	32,549	862	137	15	4	957
You can now run Kimi K2 locally with our Dynamic 1.8-bit GGUFs! We shrank the full 1.1TB model to just 245GB (-80% siz…	@UnslothAI	Company	Original	2025-07-14	130,787	1,570	251	48	51	822
Mistral releases Devstral 2507, the best open-source model for coding agents! 🔥 The 24B model is now the #1 open LLM o…	@UnslothAI	Company	Quote	2025-07-10	25,821	408	72	8	4	178
We made step-by-step guides to Fine-tune & Run every single LLM! 🦥 What you'll learn: • Technical analysis + Bug fixes…	@UnslothAI	Company	Original	2025-07-08	50,119	1,124	195	18	11	966
We’ve teamed up with @GoogleDeepMind for a challenge with a $10,000 Unsloth prize! 🦥 Show off your best fine-tuned Gem…	@UnslothAI	Company	Original	2025-07-02	47,351	550	89	9	19	288
You can now fine-tune Gemma 3n for free with our notebook! Unsloth makes Google Gemma training 1.5x faster with 50% le…	@UnslothAI	Company	Original	2025-07-01	86,539	912	170	10	12	649
Run Gemma 3n locally with our Dynamic GGUFs!✨ @Google's Gemma 3n supports audio, vision, video & text and the 4B model…	@UnslothAI	Company	Quote	2025-06-26	36,930	495	84	9	8	242
We made a Guide on mastering LoRA Hyperparameters, so you can learn to fine-tune LLMs correctly! Learn to: • Train sma…	@UnslothAI	Company	Original	2025-06-24	25,205	674	124	13	3	518
Mistral releases Small 3.2 (24B), a new update to their 3.1 model. 🔥 The model performs much better on 5-shot MMLU (Co…	@UnslothAI	Company	Original	2025-06-21	22,581	287	43	3	2	83
We're teaming up with @Google for a Gemma developer meetup at Google's San Francisco office next Thursday, June 26! 🦥 …	@UnslothAI	Company	Original	2025-06-19	26,748	278	25	10	6	32
We made a complete Guide on Reinforcement Learning for LLMs! Learn about: • RL's goal & why it's key to building i…	@UnslothAI	Company	Original	2025-06-17	68,507	1,111	205	21	15	1,029
Mistral releases Magistral, their new reasoning models! Magistral-Small-2506 excels at mathematics and coding. You ca…	@UnslothAI	Company	Quote	2025-06-10	30,623	470	87	9	3	152
Finetune DeepSeek-R1-0528-Qwen3 with GRPO using our free notebook! Our new reward function increases multilingual (or …	@UnslothAI	Company	Original	2025-06-06	54,666	1,029	160	7	9	694
We made a repo with 100+ Fine-tuning notebooks all in once place! Has guides & examples for: • Tool-calling, Classific…	@UnslothAI	Company	Original	2025-06-04	81,941	1,545	293	29	20	1,574
You can now run DeepSeek-R1-0528 with our Dynamic 1-bit GGUFs! 🐋 We shrank the full 715GB model to just 185GB (-75% si…	@UnslothAI	Company	Original	2025-05-30	46,728	723	108	23	18	278
We just crossed 10 million monthly downloads on @HuggingFace! 🦥🤗 It's all thanks to you guys - the amazing community, …	@UnslothAI	Company	Original	2025-05-28	29,980	425	45	25	3	37
Mistral releases Devstral, a new model for coding agents. Devstral-Small-2505 is now the #1 open-source LLM on SWE-Ben…	@UnslothAI	Company	Quote	2025-05-21	21,666	268	51	9	3	94
Thank you @Google for demoing how to fine-tune Gemma 3 with Unsloth, free on Colab! 🦥 #GoogleIO https://t.co/3Ab4NCghCZ	@UnslothAI	Company	Original	2025-05-20	50,199	961	87	18	8	653
You can now finetune Sesame-CSM (1B) for free with our notebook! Clone voices, learn new emotions, tones & styles. Un…	@UnslothAI	Company	Original	2025-05-20	31,504	730	122	8	5	507
You can now fine-tune TTS models with Unsloth! Train, run and save models like Sesame-CSM and OpenAI's Whisper locally…	@UnslothAI	Company	Original	2025-05-15	126,521	1,005	164	24	23	709
We're releasing a new advanced GRPO notebook for Qwen3. Learn about: • Fine-tuning Qwen3-Base to enable reasoning • Pr…	@UnslothAI	Company	Original	2025-05-13	47,170	851	145	16	11	519
You can now fine-tune Qwen3 (14B) for free with our notebook! Unsloth makes Qwen3 finetuning 2x faster with 70% less V…	@UnslothAI	Company	Original	2025-05-02	194,028	1,684	297	21	18	1,358
We partnered with @AIatMeta on a free notebook that turns your documents into high-quality synthetic datasets using Lla…	@UnslothAI	Company	Original	2025-05-01	43,163	747	134	17	15	668
Microsoft releases Phi-4 reasoning models! You can now run them locally with our Dynamic GGUFs. Phi-4-reasoning-plus …	@UnslothAI	Company	Quote	2025-05-01	83,433	995	151	12	10	521
You can now Run Qwen3 locally with our Dynamic GGUFs! 🌠 With 128K Context Length added. Our Dynamic 2.0 GGUFs achieve…	@UnslothAI	Company	Quote	2025-04-28	60,417	598	96	12	8	190
We’re excited to showcase all the amazing ways you’ve been building with Llama + Unsloth at LlamaCon 2025! 🦥🦙 Get read…	@UnslothAI	Company	Original	2025-04-25	7,794	111	4	5	1	17
Introducing Unsloth Dynamic v2.0 GGUFs! Dynamic v2.0 quants sets new benchmarks on 5-shot MMLU and KL Divergence, mean…	@UnslothAI	Company	Original	2025-04-24	59,836	471	100	13	13	182
We made a Guide on how to create Datasets for Fine-tuning! Learn to: • Curate high-quality datasets (with best practic…	@UnslothAI	Company	Original	2025-04-15	56,683	1,205	205	21	15	1,074
You can now run Llama 4 on your local device!🦙 We shrank Maverick (402B) from 400GB to 122GB (-70%). Scout: 115GB to 3…	@UnslothAI	Company	Original	2025-04-08	141,683	797	120	35	22	310
We partnered with @HuggingFace to teach you how to fine-tune LLMs with GRPO! Learn about: • Reward functions + creatin…	@UnslothAI	Company	Original	2025-03-31	99,165	1,236	212	18	11	1,116
Fine-tune Orpheus-TTS for free with our notebook! Orpheus delivers human-like speech with emotional cues (sighs, laugh…	@UnslothAI	Company	Original	2025-03-27	59,830	906	148	16	6	715
You can now Run DeepSeek-V3-0324 locally using our 2.71-bit Dynamic GGUF! We shrank 720GB to 231GB (-70%) by selective…	@UnslothAI	Company	Original	2025-03-26	46,758	882	158	21	11	309
We teamed up with @HuggingFace to release a free notebook for fine-tuning Gemma 3 with GRPO! Learn to: • Enable reason…	@UnslothAI	Company	Original	2025-03-19	92,641	1,412	230	20	13	1,029
You can now fine-tune Gemma 3 for free with our notebook! Unsloth makes Gemma 3 finetuning 1.6x faster with 60% less V…	@UnslothAI	Company	Original	2025-03-14	128,774	2,139	316	47	21	1,730
We made a Guide to teach you how to Fine-tune LLMs correctly! Learn about: • Choosing the right parameters & train…	@UnslothAI	Company	Original	2025-03-10	94,157	1,773	333	29	14	1,709
Unsloth now works on Windows! 🦥 Fine-tune LLMs locally on Windows without Linux or WSL. Tutorial: https://t.co/WhG6go…	@UnslothAI	Company	Original	2025-03-05	32,651	628	91	31	11	221
Tutorial: Train your own Reasoning LLM for free! Make Llama 3.1 (8B) have chain-of-thought with DeepSeek's GRPO. Unslo…	@UnslothAI	Company	Original	2025-02-25	63,447	1,422	252	32	10	1,135
Today, we’re launching new algorithms that enable 10x longer context lengths & 90% less VRAM for training Reasoning Mod…	@UnslothAI	Company	Original	2025-02-20	157,832	1,653	267	94	38	873
Train your own reasoning LLM using DeepSeek's GRPO algorithm with our free notebook! You'll transform Llama 3.1 (8B) t…	@UnslothAI	Company	Original	2025-02-12	100,610	2,083	356	22	11	1,856
Unsloth is the #1 trending repo on GitHub! 🦥 It’s been an incredible journey and we couldn’t have done it without you!…	@UnslothAI	Company	Original	2025-02-10	42,259	490	55	23	8	129
You can now reproduce DeepSeek-R1's reasoning on your own local device! Experience the "Aha" moment with just 7GB VRAM…	@UnslothAI	Company	Original	2025-02-06	1,221,879	3,497	532	151	116	3,291
Run DeepSeek-R1 (671B) locally on @OpenWebUI - Full Guide No GPU required. Using our 1.58-bit Dynamic GGUF and llama.c…	@UnslothAI	Company	Original	2025-01-31	67,690	835	175	16	12	790
Introducing 1.58bit DeepSeek-R1 GGUFs! 🐋 DeepSeek-R1 can now run in 1.58-bit, while being fully functional. We shrank …	@UnslothAI	Company	Original	2025-01-27	687,861	3,404	575	127	158	1,827
DeepSeek-R1 GGUF's are now on @HuggingFace! Includes all Llama & Qwen distilled models + 2 to 8-bit quantized versions…	@UnslothAI	Company	Original	2025-01-20	69,167	547	110	19	10	197
You can finetune Phi-4 for free on @Kaggle now! You'll learn how to: • Prepare your dataset • Train Phi-4 via Kaggle's…	@UnslothAI	Company	Original	2025-01-16	28,095	621	93	9	2	422
You can finetune Phi-4 for free on Colab now! Unsloth finetunes LLMs 2x faster, with 70% less VRAM, 12x longer context…	@UnslothAI	Company	Original	2025-01-10	60,284	1,177	209	22	11	936
Phi-4, including GGUF + 4-bit + 16-bit versions are now on @HuggingFace! We found & fixed 4 bugs in Phi-4 & Llamafied …	@UnslothAI	Company	Original	2025-01-08	22,977	278	53	11	3	82
Deepseek V3, including GGUF + bf16 versions are now on @HuggingFace! Min. requirements to run: 48GB RAM + 250GB of dis…	@UnslothAI	Company	Original	2025-01-07	43,186	567	83	16	9	225

Plushcap, by Matt Makai. 2021-2026.