Meet North Micro Vision: A 2.4B Native-Resolution Vision-Language Model
• 39
Inference Provider
VERIFIED
61,812 monthly requests
AI & ML interests
None defined yet.
Recent Activity
View all activity
Papers
Tiny Aya: Bridging Scale and Multilingual Depth
EAGER: Entropy-Aware GEneRation for Adaptive Inference-Time Scaling
Articles
Introducing Cohere Parse 5
#1 opened 3 days ago
by 
elcohere
dennis-zhao
updated a
Space 3 days ago
dennis-zhao
published a
Space 3 days ago
Strip zero MoE bias tensors so vLLM v0.25 can load W4A4
#7 opened 13 days ago
by 
zshen-cohere
Strip zero MoE bias tensors so vLLM v0.25 can load W4A4
#7 opened 13 days ago
by zshen-cohere
Add {% generation %} markers for assistant-only loss masking
🤝 1
#2 opened 14 days ago
by 
qgallouedec
Add a response_template for parsing assistant responses
#1 opened 14 days ago
by qgallouedec
d-rau
updated a
model 16 days ago
Article
Meet North Micro Vision: A 2.4B Native-Resolution Vision-Language Model
CohereLabs
• • 39 d-rau
published a
model 18 days ago
danielhanchen
posted an update 19 days ago
Post
5414
Introducing Unsloth Desktop 🦥
The first desktop app to run and train models locally.
• Open-source. Runs on Mac, Windows and Linux
• Supports MLX, diffusion image/video, audio, GGUF
• Connect Claude Code and Codex to local LLMs
• 50% more accurate, self-healing tool calls + sandboxed code exec
• Works for CPU + multiGPU setups - NVIDIA, AMD, Intel, Mac
• Train models 2× faster with 70% less VRAM
• Private web search, deep research, RAG, MCP and exports (NVFP4, GGUF)
• Use Unsloth’s OpenAI-compatible API and cloud models
• Securely deploy LLMs remotely and access anywhere
Unsloth Desktop is now available on http://unsloth.ai
and GitHub.
GitHub: https://github.com/unslothai/unsloth
Blog and Guide: https://unsloth.ai/docs/desktop
The first desktop app to run and train models locally.
• Open-source. Runs on Mac, Windows and Linux
• Supports MLX, diffusion image/video, audio, GGUF
• Connect Claude Code and Codex to local LLMs
• 50% more accurate, self-healing tool calls + sandboxed code exec
• Works for CPU + multiGPU setups - NVIDIA, AMD, Intel, Mac
• Train models 2× faster with 70% less VRAM
• Private web search, deep research, RAG, MCP and exports (NVFP4, GGUF)
• Use Unsloth’s OpenAI-compatible API and cloud models
• Securely deploy LLMs remotely and access anywhere
Unsloth Desktop is now available on http://unsloth.ai
and GitHub.
GitHub: https://github.com/unslothai/unsloth
Blog and Guide: https://unsloth.ai/docs/desktop
- 6 replies
danielhanchen
posted an update 24 days ago
Post
2271
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
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
danielhanchen
posted an update 30 days ago
Post
2308
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
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 about 1 month ago
Post
4653
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
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
danielhanchen
posted an update about 1 month ago
Post
5271
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
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 about 1 month ago
Post
6265
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
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
danielhanchen
posted an update about 2 months ago
Post
4985
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
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
danielhanchen
posted an update about 2 months ago
Post
4461
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
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
danielhanchen
posted an update about 2 months ago
Post
6456
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
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