Unsloth AI

686 posts

Unsloth AI banner
Unsloth AI

Unsloth AI

@UnslothAI

Train and run models locally! 🦥 https://t.co/2kXqhhvLsb

San Francisco, CA Katılım Kasım 2023
467 Takip Edilen73.7K Takipçiler
Sabitlenmiş Tweet
Unsloth AI
Unsloth AI@UnslothAI·
Introducing Unsloth Studio ✨ A new open-source web UI to train and run LLMs. • Run models locally on Mac, Windows, Linux • Train 500+ models 2x faster with 70% less VRAM • Supports GGUF, vision, audio, embedding models • Auto-create datasets from PDF, CSV, DOCX • Self-healing tool calling and code execution • Compare models side by side + export to GGUF GitHub: github.com/unslothai/unsl… Blog and Guide: unsloth.ai/docs/new/studio Available now on Hugging Face, NVIDIA, Docker and Colab.
English
234
883
5.4K
1.7M
Unsloth AI
Unsloth AI@UnslothAI·
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. The 1-bit GLM-5.2 GGUF ran locally on a Mac Studio M3 Ultra with 256GB RAM at ~21.6 tok/s. Which output do you like best? GGUF: huggingface.co/unsloth/GLM-5.…
Unsloth AI@UnslothAI

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% size). Run on a 256GB Mac or RAM/VRAM setups. GLM-5.2 is the strongest open model to date. Guide: unsloth.ai/docs/models/gl… GGUF: huggingface.co/unsloth/GLM-5.…

English
124
235
2.5K
1M
Unsloth AI
Unsloth AI@UnslothAI·
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% size). Run on a 256GB Mac or RAM/VRAM setups. GLM-5.2 is the strongest open model to date. Guide: unsloth.ai/docs/models/gl… GGUF: huggingface.co/unsloth/GLM-5.…
Unsloth AI tweet media
Z.ai@Zai_org

Introducing GLM-5.2: Frontier Intelligence, Open Weights - Significant improvements in coding and agentic tasks - Strong long-horizon capabilities with a 1M context window - Two levels of reasoning effort: GLM-5.2 (max) pushes the limits, while GLM-5.2 (high) strikes a strong balance between performance and token efficiency - MIT-licensed open weights - Same API pricing as GLM-5.1 Tech Blog: z.ai/blog/glm-5.2 Weights: huggingface.co/zai-org/GLM-5.2 API: docs.z.ai/guides/llm/glm… Coding Plan: z.ai/subscribe Chat: chat.z.ai

English
270
855
7.2K
1.7M
Unsloth AI
Unsloth AI@UnslothAI·
@googlegemma Excited to see the local community do more fine-tunes of Gemma models! 🥰
English
0
0
13
1.6K
Google Gemma
Google Gemma@googlegemma·
Want to teach Gemma to master chess? Check out this awesome community project showing how to fine-tune Gemma 4 12B on your own data, 100% locally! Running text, images, and audio on just 8GB VRAM makes custom models more accessible than ever.
English
34
226
2.4K
154.2K
Unsloth AI
Unsloth AI@UnslothAI·
You can now run Kimi K2.7 Code locally! 🌘 We shrank the 1T model to 325GB (-48%) via Dynamic 2-bit where important layers are upcasted. Run at >40 tok/s on 330GB RAM/VRAM setups. Run full precision on 610 GB. Guide: unsloth.ai/docs/models/ki… GGUF: huggingface.co/unsloth/Kimi-K…
Unsloth AI tweet media
Kimi.ai@Kimi_Moonshot

🌘 Kimi-K2.7-Code, our latest coding model, is now released and open-sourced! 🔷 Improved coding & agent performance over K2.6: +21.8% on Kimi Code Bench v2, +11.0% on Program Bench, and +31.5% on MLS Bench Lite. 🔷 Reasoning efficiency: Less overthinking, with 30% lower reasoning-token usage compared to K2.6. 🔷 Long-horizon coding: Improved instruction following, higher end-to-end coding task success rates. ⚡️ 6x High-Speed Mode coming soon! 🔌 Available today via Kimi API and Kimi Code. 🔗 Kimi Code: kimi.com/code 🔗 API: platform.moonshot.ai

English
171
304
2.9K
1.4M
Unsloth AI retweetledi
Ivan Fioravanti ᯅ
Ivan Fioravanti ᯅ@ivanfioravanti·
Local AI in action! MiniMax M3 unning locally on a single M3 Ultra 512GB in Unsloth Studio! 🔥 Here UD-Q5_K_XL decoding at 32.5 toks/s!
English
21
15
264
30.6K
Unsloth AI
Unsloth AI@UnslothAI·
MiniMax M3 can now be run locally!🔥 MiniMax-M3 is a new 428B (23B active) open model with 1M context that performs on par with Gemini 3.1 Pro. Run Dynamic 2-bit GGUF on 138GB RAM/VRAM or 3-bit on 165GB. GGUF: huggingface.co/unsloth/MiniMa… Guide: unsloth.ai/docs/models/mi…
Unsloth AI tweet media
MiniMax (official)@MiniMax_AI

MiniMax M3, Open-Weight, Now On Hugging Face , with only ~428B parameters and ~23B activated parameters Weights: huggingface.co/MiniMaxAI/Mini… MiniMax Sparse Attention: huggingface.co/papers/2606.13…

English
62
99
797
183.3K
MiniMax (official)
MiniMax (official)@MiniMax_AI·
MiniMax M3, Open-Weight, Now On Hugging Face , with only ~428B parameters and ~23B activated parameters Weights: huggingface.co/MiniMaxAI/Mini… MiniMax Sparse Attention: huggingface.co/papers/2606.13…
MiniMax (official)@MiniMax_AI

Introducing MiniMax M3: The First Open-Weights Model to Combine Three Frontier Capabilities - Coding & Agentic Frontier: 59.0% SWE-Bench Pro, 66.0% Terminal Bench 2.1, 34.8% SWE-fficiency, 28.8% KernelBench Hard, 74.2% MCP Atlas - MiniMax Sparse Attention scales context to 1M - Natively Multimodal from Step Zero API: platform.minimax.io Token Plan: platform.minimax.io/subscribe/toke… 🚀New! MiniMax Code: code.minimax.io Weights & Tech Report in ~10 Days

English
113
330
2.8K
685.8K
Unsloth AI
Unsloth AI@UnslothAI·
DiffusionGemma can now run at 2000+ tokens/sec! ⚡ We made local DiffusionGemma inference 1.8× faster. Run it on 18GB RAM via Unsloth Studio. GitHub: github.com/unslothai/unsl… Guide: unsloth.ai/docs/models/di…
Unsloth AI@UnslothAI

Google releases DiffusionGemma.✨ The new 26B-A4B diffusion text model runs locally on 18GB RAM. It supports high-speed text generation, thinking, image, video and 256K context. Run and train via Unsloth Studio. GGUF: huggingface.co/unsloth/diffus… Guide: unsloth.ai/docs/models/di…

English
64
186
1.7K
175.5K
Unsloth AI
Unsloth AI@UnslothAI·
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× faster with no accuracy loss. Gemma 4 12B MTP can run at 162 t/s vs. 52 t/s without MTP. 31B reaches 101 t/s. GGUFs + Guide: unsloth.ai/docs/models/mtp
Unsloth AI tweet media
English
61
257
2.2K
218.3K
Google Gemma
Google Gemma@googlegemma·
Meet DiffusionGemma! An experimental open model that explores a fast approach to text generation, released under an Apache 2.0 license. Moving beyond sequential, token-by-token processes to generate entire blocks of text simultaneously. Here’s what’s new with DiffusionGemma: 👇
English
166
810
5K
953.5K
Unsloth AI
Unsloth AI@UnslothAI·
Google releases DiffusionGemma.✨ The new 26B-A4B diffusion text model runs locally on 18GB RAM. It supports high-speed text generation, thinking, image, video and 256K context. Run and train via Unsloth Studio. GGUF: huggingface.co/unsloth/diffus… Guide: unsloth.ai/docs/models/di…
Unsloth AI tweet media
Google Gemma@googlegemma

Meet DiffusionGemma! An experimental open model that explores a fast approach to text generation, released under an Apache 2.0 license. Moving beyond sequential, token-by-token processes to generate entire blocks of text simultaneously. Here’s what’s new with DiffusionGemma: 👇

English
66
249
1.9K
329.9K
Unsloth AI
Unsloth AI@UnslothAI·
Google releases Gemma 4 QAT. ✨ You can now run Gemma 4 at 3x less memory with near original performance. Quantization-Aware Training (QAT) makes it possible to run Gemma 4 26B-A4B on 16GB RAM. GGUFs: huggingface.co/collections/un… QAT Guide: unsloth.ai/docs/models/ge…
Unsloth AI tweet media
Google Gemma@googlegemma

We just dropped Gemma 4 Quantization-Aware Training (QAT) checkpoints on Hugging Face! All Gemma 4 model sizes and their drafters are now optimized with QAT to cut memory requirements and maximize on-device performance!

English
93
410
2.9K
251K
Google Gemma
Google Gemma@googlegemma·
We just dropped Gemma 4 Quantization-Aware Training (QAT) checkpoints on Hugging Face! All Gemma 4 model sizes and their drafters are now optimized with QAT to cut memory requirements and maximize on-device performance!
English
95
280
2.9K
507.3K
NVIDIA AI
NVIDIA AI@NVIDIAAI·
Today we're shipping Nemotron 3 Ultra. A 550B MoE frontier-intelligence open model built for long-running agents. It delivers 5x faster inference and lowers the cost of complex agentic tasks by up to 30% versus other open frontier models.
English
202
463
3.5K
1.3M
Unsloth AI
Unsloth AI@UnslothAI·
You can now run NVIDIA Nemotron 3 Ultra, a new 550B open model. Nemotron-3-Ultra-550B-A55B is NVIDIA's largest LLM yet, with 1M context, frontier coding & chat. Run 2-bit on 200GB RAM, 3-bit on 256GB, 8-bit on 600GB. GGUF: huggingface.co/unsloth/NVIDIA… Guide: unsloth.ai/docs/models/ne…
Unsloth AI tweet media
NVIDIA AI@NVIDIAAI

Today we're shipping Nemotron 3 Ultra. A 550B MoE frontier-intelligence open model built for long-running agents. It delivers 5x faster inference and lowers the cost of complex agentic tasks by up to 30% versus other open frontier models.

English
23
46
414
40K
Unsloth AI
Unsloth AI@UnslothAI·
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 >6GB RAM via Unsloth Studio. GitHub: github.com/unslothai/unsl…
Unsloth AI@UnslothAI

Gemma 4 12B can now run locally on just 8GB RAM via Dynamic GGUFs. Google's new model, Gemma 4 12B Unified supports image, audio and 256K context. You can run and train the model via Unsloth Studio. GGUF: huggingface.co/unsloth/gemma-… Guide: unsloth.ai/docs/models/ge…

English
45
194
1.6K
142.6K
Unsloth AI
Unsloth AI@UnslothAI·
Vision and audio support for Gemma 4 12B GGUF is now added. Please update to the latest version of Unsloth and llama.cpp. 🙏
Unsloth AI tweet media
English
2
7
70
7.4K
Unsloth AI
Unsloth AI@UnslothAI·
Gemma 4 12B can now run locally on just 8GB RAM via Dynamic GGUFs. Google's new model, Gemma 4 12B Unified supports image, audio and 256K context. You can run and train the model via Unsloth Studio. GGUF: huggingface.co/unsloth/gemma-… Guide: unsloth.ai/docs/models/ge…
Unsloth AI tweet media
Google Gemma@googlegemma

Meet Gemma 4 12B! A unified, encoder-free multimodal model designed to bring high-performance intelligence directly to your laptop, and released under an Apache 2.0 license. Bridging the gap between edge efficiency and advanced reasoning. Here is what’s new with Gemma 4 12B: 👇

English
96
380
2.8K
351.7K

Keşfet

@googlegemma @MiniMax_AI @NVIDIAAI @elonmusk @BarackObama @taylorswift13 @cristiano @BillGates