AI projects from Hugging Face

Meta-Llama-3.1-8B-Instruct-AWQ-INT4

hugging-quants · Kit

Runs Meta's Llama 3.1 8B Instruct chat model in 4-bit AWQ form, so it fits on a GPU with about 4 GiB of free memory for the weights. For developers who want a…

officialmobai_Rostam-S1-4B-GGUF

bartowski · Kit

GGUF quantizations of Rostam-S1-4B, a 4B reasoning model for math, physics, software work and Persian-English text. For people who run small models locally and…

Hemmingway-1.5 GGUF

bartowski · Kit

Imatrix GGUF quantizations of HemmingwayAI's Hemmingway-1.5, a 27B text model with MTP speculative decoding and a reasoning-effort prompt format. For people wh…

Phi-4-mini-instruct

microsoft · Kit

A 3.8B open instruction model from Microsoft with a 128K token context, built for reasoning, math and logic in tight memory or latency budgets. It suits develo…

Qwen3.8-9B-Distill

empero-ai · Kit

Reasons step by step through math, code and general questions, opening each answer with a thinking block. A 9B Qwen3.5 model trained on traces from a larger Qw…

Ornith-1.5-35B-A3B-NVFP4

ornith-ai · Kit

Writes code and handles terminal agent tasks, a mixture-of-experts model using about 3B parameters per token, packaged as an NVFP4 copy. For developers hosting…

gemma-4-26B-A4B-it Cactus CQ

Cactus-Compute · Kit

2-bit, 3-bit and 4-bit compressed copies of Google's gemma-4-26B-A4B-it chat model in the Cactus weights format. Built to run on ARM devices through the Cactus…

Groot-19B-A3B-TTQ-GGUF

TokenTinkerer · Kit

Offers eleven GGUF sizes of the Groot-19B-A3B reasoning model for llama.cpp, from 7.88 to 18.59 GiB, plus a vision projector. Made for people who run the model…

zeta-2.1

zed-industries · Kit

Predicts how the code around your cursor should be rewritten next, from the file context and your recent edits. A model from Zed Industries for people building…

Qwen3.8-27B-DFlash2-GGUF by z-lab

z-lab · Kit

A draft model in GGUF form that speeds up Qwen3.8-27B by proposing token blocks for the main model to verify. For people who run that model locally with llama.…

LocalAlign_llama3.1_8B

yuyangGong · Kit

A LoRA adapter for Llama-3.1-8B-Instruct that trains it to follow trusted instructions and ignore commands hidden in external data. A prompt injection defense…

Yalda Embedding

Yaldat · Kit

Turns Persian text into 1,024-number embeddings for semantic search and retrieval. Built for developers who need to match Persian questions to the right passag…

MiMo-V2.6-Pro-MOPD

XiaomiMiMo · Kit

Handles text, image, video and audio with a 1T-parameter mixture of experts tuned to repeat tool calls less in agent work. For teams that can host models of th…

Spark-X2.6-4B-FP8

XHToken · Kit

Compact 4.1B-parameter text model in FP8 form for on-device use, with three thinking levels (none, low, high) and English and Chinese support. Aimed at coding…

Spark-X2.6-1.7B-Base

XHToken · Kit

A compact 1.7B language model for on-device use in English and Chinese, with gains in coding, agent tasks and long context, and three adjustable thinking level…

Spark-X2.5-4B

XHToken · Kit

A compact 4.1B general-purpose language model with a native 1M-token context, over 200 languages and a hybrid attention design, tuned for coding and agent use.…

Qwen3-30B-A3B-GGUF by unsloth

unsloth · Kit

GGUF files of Qwen3-30B-A3B, quantized by unsloth, for running a local chat and reasoning model in llama.cpp, Ollama or Open WebUI, with a thinking mode you ca…

Qwen3-14B-GGUF

unsloth · Kit

Gives you Qwen3 14B, a text generation model that can think through hard questions or answer fast, as GGUF files for your own computer. Packaged by unsloth for…

Llama-3.2-3B-Instruct-GGUF by unsloth

unsloth · Kit

Chats, summarizes and answers questions with Meta's compact Llama 3.2 3B instruct model, in GGUF files by Unsloth from 2-bit up to 16-bit. Small enough for ord…

gpt-oss-120b-GGUF

unsloth · Kit

Runs OpenAI's open-weight gpt-oss-120b, a 117B model with 5.1B active parameters, from GGUF files by Unsloth that carry its fixes. Built for reasoning, agent t…

gemma-3-270m-it-GGUF

unsloth · Kit

Generates text from prompts as a 268M instruction-tuned Gemma 3 model in GGUF format, small enough for laptops and desktops. For developers who want a tiny loc…

ERNIE-4.5-21B-A3B-Thinking-GGUF

unsloth · Kit

Works through logic, math, science and coding problems with a 21B mixture-of-experts model that activates 3B parameters per token, in GGUF files by Unsloth. Su…

Hy-Memory-30B-A3B

tencent · Kit

Writes an assistant's long-term memory, choosing what to keep and how to update it inside Mem0, MemOS or Hy-Memory, with about 3B active parameters. For develo…

Qwen3.8-27B-Longbook27-v2

summerAIO · Kit

Summarizes, answers questions about and continues book-length text with a fine-tuned 27B model that uses Gated DeltaNet layers, in English and Japanese. For pe…

Mica v0.1 4B

sky7350 · Kit

Gives a probability for each allowed answer to a question about a given state, as yes/no, a choice or a score, without writing text. For developers who add qui…

BeeLLM

schizophyllume · Kit

Offers a family of tiny GGUF language models that talk in bee buzzes, from buzz-only bees to mood-tagged ones and linked queen and worker hives. For hobbyists…

Sarvam-30B

sarvamai · Kit

A mixture-of-experts language model from Sarvam AI with 32.2B parameters and 2.4B active per token, built for practical use in English and many Indian language…

Sarvam-105B GGUF

sarvamai · Kit

The GGUF version of Sarvam-105B, a large mixture-of-experts model with a focus on Indian languages, split into 9 shards at 4-bit for llama.cpp. For people with…

Qwen3-4B P9 Honeypot

samliumay · Kit

A small research adapter for Qwen3-4B that turns the model into a decoy. It sends a silent alert to a local collector when it spots an attack on its secrets, t…

MiMo-V2.6-Distill-Qwen-9B-GSQ-RCO-GGUF

sainez · Kit

Gives you a 9B coding and tool-calling model as one 3.64 GiB GGUF file, quantized at about 3.5 bits per weight for running on your own machine.

Flint INT4

RecursiveSI · Kit

A 4-bit MLX copy of Recursive Flint for local use on Apple Silicon, about 22.6 GB, launched through Rec with pi or OpenCode. Suits Mac users and developers who…

gemma-4-31B-it-scotoma-2

ReadyArt · Kit

Text generation model of 31.3B parameters from ReadyArt, built on Google's gemma-4-31b-it and stored as Safetensors. Its page gives no statement of purpose, so…

Qwen3-8B-MLX-bf16

Qwen · Kit

Runs the Qwen3 8B language model through the mlx library for chat, reasoning, translation and agent work. Suits developers who want a local text model with a s…

Qwen3-30B-A3B-GGUF

Qwen · Kit

A 30.5B mixture-of-experts chat model in GGUF format with only 3.3B parameters active per token, runnable in llama.cpp or ollama. It has thinking and plain mod…

Qwen3-0.6B-GGUF

Qwen · Kit

A small 0.6B chat model in GGUF format that runs locally in llama.cpp or ollama and can switch between thinking and plain replies. Suits people with modest har…

Qwen2.5-Coder-7B

Qwen · Kit

Completes and generates code as a 7.6B base language model that developers can run, fine-tune or use for fill in the middle tasks. Built for people making codi…

Qwen2.5-Coder-32B-Instruct-GGUF

Qwen · Kit

GGUF copy of a 32B code chat model that runs locally with llama.cpp. It writes, explains and fixes code from plain requests, for developers who want to run it…

Qwen2.5-Coder-0.5B-Instruct

Qwen · Kit

Writes, explains and fixes code as a tiny 494M-parameter chat model with a 32,768-token context. Suits developers who want the smallest open Qwen coding model…

Qwen2.5-7B-Instruct-AWQ

Qwen · Kit

A 4-bit AWQ build of Qwen2.5-7B-Instruct, a 7.6B chat model that follows instructions, handles tables and returns JSON. For developers who want a capable chat…

Qwen2.5-14B-Instruct

Qwen · Kit

Answers questions, writes code, does maths and returns structured JSON as a 14.7B-parameter chat model with a context window up to 131,072 tokens. Suits develo…

Qwen2.5-0.5B

Qwen · Kit

The smallest base model in Qwen2.5, about 494M parameters with a 32,768-token context, meant for further training on your own data. For developers who want a t…

Limite 1B - Violetto

paradigma-inc · Kit

Solves hard math problems with a 1B-parameter model trained from scratch for fast, high-volume reasoning. It suits developers who run math workloads on an NVID…

Raptor-0.6-4B-JANG_6M

OsaurusAI · Kit

Decides when to call a tool, when to answer directly and when to ask first, tuned from a 4B model and quantized for Apple Silicon Macs running Osaurus. For peo…

LFM2.5-350M-home-assistant-sft

OrdenWills · Kit

Turns plain home commands such as turn off the TV into structured tool calls, checking device states first. A 350M model for smart home builders and tinkerers.

MOSS-Video-Preview-Real-Time-SFT

OpenMOSS-Team · Kit

Comments on video while it plays, taking frames one by one and answering with low delay. For developers and researchers building live video assistants in Pytho…

Luciole-8B-Instruct-1.1-GGUF

OpenLLM-France · Kit

Quantized GGUF copy of Luciole-8B-Instruct-1.1, an 8B text generation model for French and English, for running on your own computer. From LINAGORA's work in t…

Octen-WebGR-0.6B

Octen · Kit

Turns a short search query into the web address it most likely means, using a table of 30.9 million URLs stored with the model. For developers and researchers…

Hermes-4.3-36B-GGUF

NousResearch · Kit

A 36B hybrid reasoning model in GGUF form that can think before it answers, write valid JSON and follow your system prompt. For people who run a large model on…

Qwen3.8-Flash-Next-DFlash2-GGUF

nazeshinjite · Kit

GGUF draft model that speeds up Qwen3.8-Flash-Next in llama.cpp through speculative decoding, in 334 MiB and 622 MiB files. It is not a standalone model, and i…

Nanbeige4.3-33B-INT4

Nanbeige · Kit

INT4 quantized version of Nanbeige4.3-33B, a 33B model for coding and professional agent tasks, made with quantization-aware training. For developers who want…

Nanbeige4.2-3B by Nanbeige

Nanbeige · Kit

Compact looped-transformer model of 4.2B parameters for agent work such as tool use, office tasks and coding, in English and Chinese. For developers who want a…

Agaram 2.5B

murai-labs · Kit

Chats in Tamil script, romanized Tamil and English, and translates between Tamil and English. A 2.5B model built from scratch by Murai Labs, for Tamil speakers…

VulnLLM-R-7B-8bit

mlx-community · Kit

Runs an 8-bit MLX copy of VulnLLM-R-7B for text generation through mlx-lm. Meant for developers who want to try the model locally. The card does not say what i…

JevK5-chat-mlx-4bit

mlx-community · Kit

A 4-bit MLX copy of the 4.2B JevK5 chat model for Apple Silicon, with a 262,144 token context and a small memory footprint. Made for Mac users who want a quick…

flint-mixed-3-4bit

mlx-community · Kit

A community MLX build of Recursive's 40B Flint coding model that shrinks the experts to 3 bits, so it fits a 24 GB or 32 GB Apple Silicon Mac. Made for develop…

Mistral-7B-v0.1

mistralai · Kit

Generates and continues text as a 7B pretrained base model, for researchers and developers who want a starting point to test, tune or build on.

Mistral-7B-Instruct-v0.1

mistralai · Kit

A 7B instruction-tuned chat model from Mistral, fine-tuned from Mistral-7B-v0.1 on public conversation datasets. Made for developers who want a small open mode…

MiroThinker-v1.0-8B

miromind-ai · Kit

An open research agent model that reasons over long contexts and calls tools many times per task to look up information. The 8B size, built on Qwen3-8B, suits…

KLM 1.5

MinimaLabs · Kit

A 99M-parameter base language model trained from scratch on 100B tokens, with a hybrid attention design. Made for researchers and tinkerers who want a tiny ope…

Phi-4-multimodal-instruct

microsoft · Kit

Compact 5.6B model that takes text, images and audio and replies in text, with a 128K token context. For developers who want speech, vision and text in one sma…

Phi-4

microsoft · Kit

A 14B open language model from Microsoft Research, tuned for reasoning and chat in English with limited compute. It suits developers who add text features to a…

Maya-1

maya-research · Kit

An open-weight text-to-speech model where you describe the voice in plain words and add inline emotion cues. It suits developers and creators who need expressi…

dale-9b (GGUF)

manuelgscom · Kit

Turns a Spanish or English request into one Linux bash command, returned as a small JSON object. For terminal users and developers who want a local command hel…

askmdb-9b-GGUF

manuelgscom · Kit

Writes a read-only MongoDB aggregate pipeline from a plain Spanish or English question. A GGUF copy of a Qwen3.5-9B fine-tune that runs locally with llama.cpp,…

Maincoder-1B

Maincode · Kit

Completes and writes Python code from a function signature or a docstring. A 1B code model from Maincode that is small enough to run on consumer hardware, for…

Qwen3.6-35B-A3B Claude 4.7 Opus Reasoning Distilled

lordx64 · Kit

Thinks in explicit think blocks before it answers, tuned on about 8k reasoning traces from Claude Opus 4.7. A 35B mixture-of-experts Qwen3.6 variant for hard m…

ColGrep-Agent-2B

lightonai · Kit

A 2.5B-parameter model that finds the files and line ranges relevant to a bug report or question about a code repository, by searching and reading the repo. Ru…

humanizer-GGUF

jialinyyzz · Kit

Rewrites AI-written drafts in English and Chinese so they read like a person wrote them, keeping numbers, dates, names and quotes. A 12B model in GGUF files fo…

Qwopus3.8-27B-Flash-GGUF

Jackrong · Kit

Cuts reasoning time and cost for long agent tasks, as a GGUF build of a Qwen3.8-27B fine-tune. Made for people who run agent loops on their own machine and wan…

Qwen3.5-4B-Claude-4.6-Opus-Reasoning-Distilled-GGUF

Jackrong · Kit

Thinks through problems step by step inside think tags, as a 4B Qwen3.5 model fine-tuned on reasoning chains and packaged as GGUF. For people who run a small r…

MLX-Qwen3.5-0.8B-Claude-4.6-Opus-Reasoning-Distilled-6bit

Jackrong · Kit

Runs a tiny 0.8B reasoning-tuned chat model in the MLX format at 6-bit, converted from Jackrong's Qwen3.5 distilled model. For people who want a tiny local mod…

Agents-A1

InternScience · Kit

Runs multi-step agent work: planning, search, tool calling and scientific reasoning, as a 35B open-weight language model. Built for developers who wire a model…

Flint-DFlash2

incoai · Kit

A 403M-parameter draft model that speeds up serving of the Flint language model with speculative decoding in SGLang, without changing its output. It is not a s…

K2-Horizon-3.7B-GGUF

IFM · Kit

GGUF files of the 3.7B K2-Horizon text model in six precision levels, from BF16 to Q4_K_M, for running with llama.cpp. The model has a 512K-token context windo…

K2-Horizon-0.9B

IFM · Kit

Answers maths, coding and science questions as a compact open reasoning model that reads up to 128K tokens at once. Built by IFM for people who want a small mo…

ibnsina-1.5b

ibnsina-llm · Kit

A small Persian language model for writing, summarizing, translating and chatting offline, trained from scratch mostly on Persian text. Runs through ollama, LM…

Granite-Docling-258M

ibm-granite · Kit

Converts document page images into structured text, with equations, layout and questions about page elements, in a 258M model from IBM Research. For people who…

Granite-4.0-H-350M

ibm-granite · Kit

Handles summaries, classification, extraction, question answering, RAG, code tasks and tool calling in 12 languages with a 340M-parameter instruct model from I…

ALLaM-7B-Instruct-preview

humain-ai · Kit

Answers questions and follows instructions in Arabic and English. A 7B model trained from scratch by the National Center for Artificial Intelligence at SDAIA,…

zephyr-7b-beta

HuggingFaceH4 · Kit

Chats as a helpful assistant, built by tuning Mistral-7B with direct preference optimization. For developers and hobbyists who want a small open chat model the…

Qwen3.6-35B-A3B-Claude-4.6-Opus-Reasoning-Distilled-GGUF

hesamation · Kit

Runs a reasoning-tuned Qwen3.6-35B-A3B on your own machine as GGUF files in four quant sizes, trained on Claude Opus 4.6 style reasoning data. For people who w…

Parallel Constrained Decoding for Apple Silicon

harshatheg · Kit

Extracts structured fields, routes decisions and classifies text on Apple Silicon with MLX, scoring every schema field at once. Cuts latency 5.6x to 7.0x on an…

Tev-320B

gordonhu · Kit

A 320B mixture-of-experts agent model that works through long terminal tasks with a single bash tool. Trained with reinforcement learning on 1,170 environments…

Qwen2.5-Coder-1.5B Q8_0 GGUF

ggml-org · Kit

Runs Qwen2.5-Coder 1.5B on your own machine as a Q8_0 GGUF file through llama.cpp, from the command line or as a local server. It suits developers who want a s…

SaulLM-54B-Instruct

Equall · Kit

A language model tuned for legal text, trained on US and European legal sources. A research release for people who study or adapt legal AI. Its answers are inf…

ARK-ASR-3B

Edge0 · Kit

Turns speech into text in many languages, with a Whisper-style audio encoder feeding a Qwen decoder. For developers and researchers who want multilingual trans…

theOG-50M

DrunkkToys · Kit

Writes a Python function from a plain English request. A 50M parameter code model trained from scratch on one laptop, small enough to run offline in Ollama, LM…

Maple-Preview

deepgrove · Kit

A 20B ternary-weight reasoning model that activates about 1B parameters per token. Built for fast on-device use, with a 5.31 GB checkpoint and 131,072 token co…

Kiyo-65M

DedeProGames · Kit

Continues English text with a tiny 65M-parameter decoder-only model trained on 80B tokens. For learners and researchers who want a small transformers model to…

Gemma-3-12b-it-MAX-HORROR-Imatrix-GGUF

DavidAU · Kit

Writes fiction with a tint of horror. GGUF builds of Gemma 3 12B instruct, quantized with an imatrix made from a horror model, for creative writers who run mod…

PLLuM-12B-chat-2512

CYFRAGOVPL · Kit

A Polish-language chat model from the PLLuM family, tuned to human preferences for dialogue, question answering and summarization, with an eye on Polish public…

Qwen 3.6 35B-A3B REAP-48 v2 GGUF

crucible-labs · Kit

Runs a pruned and quantized Qwen3.6-35B-A3B in an 8.78 GiB GGUF file for llama.cpp, closer to the unquantized weights than the first release. For people with l…

Underdog-Woof-4B-1.1

ConwayResearch · Kit

Generates text as a compact 4.2B model, post-trained from Qwen 3 4B to work better with Underdog's own setup and quantized to 4-bit for MLX. For people running…

Instinct

continuedev · Kit

Predicts the next edit you are likely to make in your code. A 7.6B model from Continue, fine-tuned from Qwen2.5-Coder-7B, for developers who want to run it on…

ConeML 1.2B Experimental

ConeML · Kit

Names the tallest, oldest or first item among facts you supply, as a small English research model in FP32 Safetensors and Q8_0 GGUF files. For researchers, non…

North Mini Code

CohereLabs · Kit

An open-weights research model from Cohere for writing code, agentic software engineering and terminal tasks. A 30B model with 3B active, 256K context. For dev…

Chroma Context-1

chromadb · Kit

A 20B-parameter search model that finds supporting documents for complex, multi-step questions and trims its own working context as it goes. Meant to act as a…

North-Mini-Code-1.0 GGUF

byteshape · Kit

GGUF copies of the North-Mini-Code-1.0 coding model, compressed with ByteShape's ShapeLearn for GPU use in llama.cpp. Four sizes from 12.1 GB to 21.5 GB, for d…

Cola DLM

ByteDance-Seed · Kit

A research text-generation model that writes through a continuous latent space, pairing a text autoencoder with a diffusion transformer. For researchers and de…

SalamandraTA-7b-instruct

BSC-LT · Kit

A 7.8B translation model for 40 languages and 3 varieties, covering sentence, paragraph and document translation plus HTML or XML text. For developers and rese…