Unofficial Mistral Community [deprecated]

community

Activity Feed Request to join this org

AI & ML interests

Unofficial org for community upload of Mistral's Open Source models.

Recent Activity

nielsr submitted a paper 6 days ago

Ultralytics YOLO26: Unified Real-Time End-to-End Vision Models

nielsr submitted a paper 14 days ago

Gemini Embedding 2: A Native Multimodal Embedding Model from Gemini

nielsr submitted a paper 20 days ago

Stable Audio 3

View all activity

danielhanchen

posted an update 2 days ago

Post

3252

Google releases Gemma 4 QAT. ✨
You can now run Gemma 4 at 3x less memory with near original performance.

QAT makes it possible to run Gemma 4 26B-A4B on 16GB RAM.

GGUFs: https://huggingface.co/collections/unsloth/gemma-4-qat
QAT Guide: https://unsloth.ai/docs/models/gemma-4/qat

1 reply

danielhanchen

posted an update 6 days ago

Post

8800

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: unsloth/gemma-4-12b-it-GGUF
Guide: https://unsloth.ai/docs/models/gemma-4

5 replies

nielsr

submitted a paper to Daily Papers 6 days ago

Ultralytics YOLO26: Unified Real-Time End-to-End Vision Models

Paper • 2606.03748 • Published 8 days ago • 10

nielsr

submitted a paper to Daily Papers 14 days ago

Gemini Embedding 2: A Native Multimodal Embedding Model from Gemini

Paper • 2605.27295 • Published 15 days ago • 23

nielsr

submitted a paper to Daily Papers 20 days ago

Stable Audio 3

Paper • 2605.17991 • Published 23 days ago • 18

danielhanchen

posted an update 20 days ago

Post

2711

Qwen3.6 MTP is here! Run locally on 20GB RAM. ⚡️

MTP enables Qwen3.6 to generate ~1.4–2.2× faster with no accuracy change.

Qwen3.6-27B: unsloth/Qwen3.6-27B-MTP-GGUF
Qwen3.6-35B-A3B: unsloth/Qwen3.6-35B-A3B-MTP-GGUF
Guide: https://unsloth.ai/docs/models/qwen3.6#mtp-guide

2 replies

danielhanchen

posted an update 28 days ago

Post

5830

We’re excited to announce that Unsloth has joined the PyTorch Ecosystem! 🔥🦥

Unsloth is an open-source project that makes training & running models more accurate and faster with less compute. Our mission is to make local AI accessible to everyone. Thanks to all of you for making this possible! 💕

Blog: https://unsloth.ai/blog/pytorch
GitHub: https://github.com/unslothai/unsloth

2 replies

danielhanchen

posted an update about 1 month ago

Post

7716

We collaborated with NVIDIA to teach you how we made LLM training ~25% faster! 🚀

Learn how 3 optimizations help your home GPU train models faster:
1. Packed-sequence metadata caching
2. Double-buffered checkpoint reloads
3. Faster MoE routing

Guide: https://unsloth.ai/blog/nvidia-collab
GitHub: https://github.com/unslothai/unsloth

danielhanchen

posted an update about 1 month ago

Post

8857

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 agentic coding on 24GB RAM

Run with self-healing tool calls, code execution, web search via the Unsloth API endpoint and llama.cpp

Guide: https://unsloth.ai/docs/basics/api

danielhanchen

posted an update about 1 month ago

Post

10815

Unsloth is now one of the top 10 most followed organizations on Hugging Face. 🤗🦥

Thanks so much for all the support!
Our HF page:

unsloth

5 replies

nielsr

submitted a paper to Daily Papers about 2 months ago

Scaling Test-Time Compute for Agentic Coding

Paper • 2604.16529 • Published Apr 16 • 12

danielhanchen

posted an update about 2 months ago

Post

5366

Qwen3.6-27B is out now! Run it locally on 18GB RAM. 💜

Qwen3.6-27B surpasses Qwen3.5-397B-A17B on all major coding benchmarks.

GGUFs to run: unsloth/Qwen3.6-27B-GGUF
Guide + MLX: https://unsloth.ai/docs/models/qwen3.6

danielhanchen

posted an update about 2 months ago

Post

2852

Qwen3.6-35B-A3B can now be run locally! 💜

The model is the strongest mid-sized LLM on nearly all benchmarks.

Run on 23GB RAM via Unsloth Dynamic GGUFs.

GGUFs to run: unsloth/Qwen3.6-35B-A3B-GGUF
Guide: https://unsloth.ai/docs/models/qwen3.6

13 replies

nielsr

submitted a paper to Daily Papers about 2 months ago

Geometric Context Transformer for Streaming 3D Reconstruction

Paper • 2604.14141 • Published Apr 15 • 21

nielsr

submitted a paper to Daily Papers 2 months ago

A Frame is Worth One Token: Efficient Generative World Modeling with Delta Tokens

Paper • 2604.04913 • Published Apr 6 • 12

danielhanchen

posted an update 2 months ago

Post

5523

You can now fine-tune Gemma 4 for free with our notebooks! 🔥

You just need 8GB VRAM to train Gemma 4 locally!

Unsloth trains Gemma4 1.5x faster with 50% less VRAM.
GitHub: https://github.com/unslothai/unsloth
Guide + Notebooks: https://unsloth.ai/docs/models/gemma-4/train

5 replies

nielsr

submitted a paper to Daily Papers 2 months ago

MDPBench: A Benchmark for Multilingual Document Parsing in Real-World Scenarios

Paper • 2603.28130 • Published Mar 30 • 11

danielhanchen

posted an update 2 months ago

Post

3856

Google releases Gemma 4. ✨
Gemma 4 introduces 4 models: E2B, E4B, 26B-A4B, 31B.
The multimodal reasoning models are under Apache 2.0.

Run E2B and E4B on ~6GB RAM, and on phones. Run 26B-A4B and 31B on ~18GB.

GGUFs: https://huggingface.co/collections/unsloth/gemma-4
Guide: https://unsloth.ai/docs/models/gemma-4

danielhanchen

posted an update 2 months ago

Post

2796

A new way to use Unsloth.

Coming soon...

MaziyarPanahi

posted an update 2 months ago

Post

3367

Training mRNA Language Models Across 25 Species for $165

We built an end-to-end protein AI pipeline covering structure prediction, sequence design, and codon optimization. After comparing multiple transformer architectures for codon-level language modeling, CodonRoBERTa-large-v2 emerged as the clear winner with a perplexity of 4.10 and a Spearman CAI correlation of 0.40, significantly outperforming ModernBERT. We then scaled to 25 species, trained 4 production models in 55 GPU-hours, and built a species-conditioned system that no other open-source project offers. Complete results, architectural decisions, and runnable code below.

https://huggingface.co/blog/OpenMed/training-mrna-models-25-species

AI & ML interests

Recent Activity

Team members 24

mistral-community's activity