AI projects from Hugging Face

Diffusion-Qwen3.8-27B

summerAIO · Kit

Generates text by parallel unmasking from Qwen3.8-27B converted into a masked diffusion language model. An experimental research checkpoint for researchers and…

DeepSeek-V4.1-Flash-1017-GSQ-RCO-GGUF

ISTA-DASLab · Kit

GGUF versions of DeepSeek-V4.1-Flash-1017 at three small sizes, with each tensor quantized at its own precision. For people running a huge mixture-of-experts m…

DeepSeek-V4.1-Flash-1017-GGUF

unsloth · Kit

Unsloth's GGUF quantizations of DeepSeek-V4.1-Flash-1017, a huge image-and-text model, for running locally on a machine with 128 GB or more of RAM. For people…

Ornith-1.5-9B-GGUF

ornith-ai · Kit

Offers GGUF files of Ornith-1.5-9B, a 9B dense model trained through a self-improvement loop, for single-GPU use. Aimed at developers who want a small model wi…

Nanbeige4.3-33B

Nanbeige · Kit

A 33.1B open model for agentic coding and professional cowork tasks, built as the flagship teacher of the Nanbeige4.3 series. For developers and agent builders…

Qwen3.8-Flash-Next-GSQ-RCO-Coder-GGUF

ISTA-DASLab · Kit

A coding-focused GGUF build of Qwen3.8-Flash-Next with half its experts removed, cutting 354 GB at BF16 to 58.4 GB while keeping image input. For people with l…

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…

Recursive Flint

RecursiveSI · Kit

A 39.8B mixture-of-experts language model for coding agents that investigates codebases, fixes bugs, adds features and writes tests. For developers who run the…

gemma-4-31B-it

google · Kit

An instruction-tuned 31B model from Google DeepMind that reads text and images and writes text, with a 256K context and configurable thinking. For developers w…

dale-0.8b-GGUF

manuelgscom · Kit

A small 4-bit GGUF model that turns a plain request in Spanish or English into one Linux bash command. It runs offline on a CPU inside the dale tool. For peopl…

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.…

Qwen3.8-Flash-Next-GSQ-RCO-GGUF

ISTA-DASLab · Kit

GGUF versions of Qwen3.8-Flash-Next at four sizes, with each tensor quantized at its own precision and a vision projector for image input. For people running a…

DeepSeek-V4.1-Flash-1017-GSQ-RCO-Coder-GGUF

ISTA-DASLab · Kit

An expert pruned and quantized GGUF of DeepSeek-V4.1-Flash-1017 from ISTA-DASLab, aimed at code and agent work, with transformer weights of 72.1 GB. Suits deve…

Unlimited-OCR

baidu · Kit

Parses document images and multi-page PDFs into text with a 3.3B vision-language model from Baidu. For developers who add OCR and document parsing to their own…

AREX-2

BAAI · Kit

Improves its own solutions over several rounds of propose, measure, reflect and revise, using a 27B model from BAAI. For agent researchers and developers worki…

Nex-N2.6

nex-agi · Kit

Handles computer use, coding and long tool-driven tasks as a multimodal agentic model built on GLM-5.3-Flash, in FP8 weights of about 321B parameters. For team…

GLM-5.3-Flash

zai-org · Kit

zai-org's natively multimodal GLM-5 series model with 320B total and 18B active parameters, with a hybrid sparse and linear attention design and a thinking bud…

DeepSeek-V4.1-Flash

deepseek-ai · Kit

DeepSeek's multimodal mixture of experts model with a 552B backbone and a one million token context, built to cut KV cache cost for long input agent work. Suit…

S5-nano

maritaca-ai · Kit

Maritaca AI's small Portuguese and English model built on Qwen3.5-4B, with Think and Instruct modes and strong tool use, in BF16 for vLLM and SGLang. Suits dev…

Raon-1 nano

KRAFTON · Kit

Generates text and follows instructions in Korean and English, keeps conversation context and calls tools. A 3.1B-parameter language model with a 262,144-token…