AI projects from Hugging Face

Mellum2.1-12B-A2.5B-Thinking

JetBrains · Kit

A 12B mixture-of-experts thinking model with 2.5B active parameters, trained with reinforcement learning on real repositories for coding agents, math and hard…

Kimi-K3.1-Pro-Coder

Grawnch · Kit

Runs a heavily compressed copy of the 2.8T-parameter Kimi-K3.1-Pro, tuned for coding and math. Made by Grawnch with a three-tier mixed-bit scheme, for people w…

Quark

FirstPrinciplesLabs · Kit

A 9B reasoning model for physics, science and maths, fine-tuned from Qwen3.5-9B by FirstPrinciples. For researchers who want step-by-step derivations and a sec…

CherryPit-1.2-2B

DRUPEs · Kit

A 2B coding and chat model built on MiniCPM5-2B that is much better at web apps needing several features in one component. For developers who want a small loca…

Qwen3.5-0.8B Astra Weight Edit

JonathanColetti · Kit

Fixes the repeat loops that Qwen3.5-0.8B falls into in thinking mode by editing two weight tensors directly, with no training. A small image-text model for Tra…

Qwen3.8-35B-A3B-Distill

empero-ai · Kit

Reasons step by step before it answers, using a 35B mixture-of-experts model that activates about 3B parameters per token. Distilled from Qwen3.8 teacher trace…

Qwen3-8B-GGUF

Qwen · Kit

Runs Qwen3-8B as quantized GGUF files in llama.cpp or Ollama, with a thinking mode for math, code and logic and a plain mode for chat. For people who want a lo…

DeepSeek-R1

deepseek-ai · Kit

Generates text with a 684B reasoning model trained mainly through reinforcement learning, aimed at math, code and logic. Suits researchers and teams who host l…

Qwen3.5-0.8B-weight-space-programming by ML-Intern-lab

ML-Intern-lab · Kit

Solves math problems step by step with a small Qwen3.5-0.8B model whose weights an LLM edited directly, with no training, to stop repetition loops. For researc…

MiniCPM5-2B

openbmb · Kit

Generates text with a dense 2B-class model made for on-device and local use, covering coding, math, long context, tool use and agent tasks in English and Chine…

Qwen3.5-0.8B-weight-space-programming

RikiyaT · Kit

Qwen3.5-0.8B with two weight matrices edited by an LLM, with no training, to stop its thinking loops and do better at math. An experimental model for researche…

Qwen3.8-27B-DSpine-b16-GGUF

aj9o9 · Kit

A GGUF draft model that speeds up Qwen3.8-27B in llama.cpp through speculative decoding, reaching about 125 tokens per second on code and math on one RTX 3090.…