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 3 days ago

A Frozen Pixel-Space Diffusion Model Can Guide Itself with Its Own Samples

alpindale authored a paper 4 days ago

Characterizing Warp Divergence from Pascal to Blackwell

nielsr submitted a paper 10 days ago

WorldDiT: A Unified Diffusion Architecture for World and Action Modeling

View all activity

danielhanchen

posted an update 1 day ago

Post

261

DeepSeek-V4-Flash can now run 2× faster locally with DSpark! ⚡️

DSpark enables V4-Flash-0731 GGUFs to generate ~1.4–2× faster with no accuracy change.

DeepSeek-V4-Flash-0731 can reach at 120 tokens/s.

GGUFs: unsloth/DeepSeek-V4-Flash-0731-GGUF
Guide: https://unsloth.ai/docs/models/deepseek-v4

nielsr

submitted a paper to Daily Papers 3 days ago

A Frozen Pixel-Space Diffusion Model Can Guide Itself with Its Own Samples

Paper • 2607.29122 • Published 8 days ago • 4

alpindale

authored a paper 4 days ago

Characterizing Warp Divergence from Pascal to Blackwell

Paper • 2607.23402 • Published 13 days ago • 9

danielhanchen

posted an update 7 days ago

Post

1317

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 whose side panel develops a visible crack and then bursts...

1-bit Kimi K3 GGUF ran locally on 4x B200s at 36 tok/s.

GGUF: unsloth/Kimi-K3-GGUF
GitHub repo: https://github.com/unslothai/unsloth

1 reply

danielhanchen

posted an update 9 days ago

Post

3946

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% size).

Run on a Mac Studio connected with 128GB RAM device. Kimi K3 is the strongest open model to date.

GGUF: unsloth/Kimi-K3-GGUF
Guide: https://unsloth.ai/docs/models/kimi-k3

5 replies

nielsr

submitted a paper to Daily Papers 10 days ago

WorldDiT: A Unified Diffusion Architecture for World and Action Modeling

Paper • 2607.23909 • Published 12 days ago • 7

alpindale

submitted a paper to Daily Papers 10 days ago

Characterizing Warp Divergence from Pascal to Blackwell

Paper • 2607.23402 • Published 13 days ago • 9

danielhanchen

posted an update 18 days ago

Post

4886

Introducing Unsloth for AMD 🚀
You can now train & run LLMs on your AMD hardware

• We collaborated with AMD to enable you to train & run 500+ models on AMD GPUs
• Works on Windows, WSL, Linux
• Train Qwen, Gemma on just 3GB VRAM

GitHub: https://github.com/unslothai/unsloth
Blog + Guide: https://unsloth.ai/docs/basics/amd

3 replies

danielhanchen

posted an update 20 days ago

Post

5923

Gemma 4 is now faster and much more accurate! 🚀

Google made huge improvements to tool-calling and chat accuracy, reliability + speed.
To get fixes, re-download our updated GGUF, MLX, NVFP4 quants!

Unsloth quants: https://huggingface.co/collections/unsloth/gemma-4
Gemma 4 Guide: https://unsloth.ai/docs/models/gemma-4

8 replies

nielsr

submitted a paper to Daily Papers 23 days ago

MonkeyOCRv2: A Visual-Text Foundation Model for Document AI

Paper • 2607.11562 • Published 26 days ago • 77

danielhanchen

posted an update 24 days ago

Post

4767

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 hits 13K tok/s (B200).

Unsloth NVFP4 enables faster, more accurate 4-bit Blackwell inference.

Blog: https://unsloth.ai/docs/basics/nvfp4
Gemma NVFP4: https://huggingface.co/collections/unsloth/nvfp4

3 replies

nielsr

submitted a paper to Daily Papers 24 days ago

Xiaomi-Robotics-U0: Unified Embodied Synthesis with World Foundation Model

Paper • 2607.11643 • Published 26 days ago • 45

danielhanchen

posted an update 28 days ago

Post

4327

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 hit 17,561 tok/s (B200).

We also improved accuracy, tool calling, agent use, and looping.

Qwen3.6 NVFP4: https://huggingface.co/collections/unsloth/nvfp4
Guide: https://unsloth.ai/docs/models/qwen3.6#nvfp4

1 reply

nielsr

submitted 2 papers to Daily Papers 29 days ago

Single-Rollout Asynchronous Optimization for Agentic Reinforcement Learning

Paper • 2607.07508 • Published about 1 month ago • 29

Sparse Delta Memory: Scaling the State of Linear RNNs through Sparsity

Paper • 2607.07386 • Published about 1 month ago • 13

nielsr

submitted 2 papers to Daily Papers about 1 month ago

SiamJEPA: On the Role of Siamese Student Encoders in JEPA

Paper • 2607.04044 • Published Jul 4 • 1

HunyuanOCR-1.5: Making Lightweight OCR VLMs Faster and Better

Paper • 2607.04884 • Published Jul 6 • 9

danielhanchen

posted an update about 1 month ago

Post

6273

DeepSeek-V4 can now run locally with Unsloth GGUFs! 🐳

Run lossless DeepSeek-V4-Flash on 168GB RAM or
3-bit works on 110GB Mac, RAM, VRAM setups.

Run via Unsloth Studio or llama.cpp.

GGUF: unsloth/DeepSeek-V4-Flash-GGUF
Guide: https://unsloth.ai/docs/models/deepseek-v4

nielsr

submitted a paper to Daily Papers about 1 month ago

Unified Audio Intelligence Without Regressing on Text Intelligence

Paper • 2607.05196 • Published Jul 6 • 23

danielhanchen

posted an update about 2 months ago

Post

3381

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: unsloth/GLM-5.2-GGUF

3 replies

AI & ML interests

Recent Activity

Team members 24

mistral-community's activity