AI projects from Hugging Face

GLM-5.3-Flash EXL3 Spark

0xSero · Kit

Runs GLM-5.3-Flash with a 256k-token context and image input on one DGX Spark, using a mixed 2.31 bits-per-weight EXL3 build. For people hosting a large model…

Qwen3.8-Flash-Next-125B-UltraLite-37GiB-GGUF

0xKitkat · Kit

Squeezes the Qwen3.8-Flash-Next mixture-of-experts model into about 37 GiB of text-only GGUF files for experiments. It needs a patched llama.cpp build that com…

Laplace-1-Atlas

JuneoAI · Kit

Helps organizations decide who does a task, who sees information, what runs and what gets accepted, by scoring candidate options in one pass. A 27.4B model bui…

AgentForesight-7B

ZBox008003 · Kit

Audits a multi-agent run while it unfolds and flags the earliest decisive error, naming the step, the agent and a short reason. For developers who build and de…

Zabibu Fikra Model 2 (4B)

zabibutechnika · Kit

Answers in Swahili and English from a 4B model made to run privately on your own device, offline. Suits on-device assistants that need African context, such as…

MiMo-V2.5-ASR

XiaomiMiMo · Kit

Transcribes speech in Mandarin, English and Cantonese, including Chinese dialects, code-switching, song lyrics, noisy audio and multi-speaker meetings, with pu…

NeoHorse-1-9B

TokenRhythm · Kit

A 9B text model post-trained from Qwen3.5-9B for agent frameworks, tool use, coding and instruction following, released as text-only weights. For developers wh…

Falcon OCR

tiiuae · Kit

Reads a document image with a small 270M-parameter model and returns the text, formulas as LaTeX or tables as HTML, including scans, receipts and handwriting.

Indic Multilingual Turn Detector

tarun7r · Kit

Reads speech-to-text transcripts to judge whether a caller has finished their turn, in English, Hinglish and seven Indic languages. For voice agent and call-ce…

MNN-Pocket-0.3B-Base

taobao-mnn · Kit

A pre-trained base language model of about 300M parameters for Chinese and English, designed with the MNN inference engine for on-device use, as a start for fu…

qwen-2.5-0.5b-block-transformer-hiba-wikitext2

tahamajs · Kit

Swaps 18 of the 24 attention layers in Qwen2.5-0.5B for a hierarchical block attention operator, then distills it on WikiText-2. A research checkpoint for stud…

qwen-2.5-0.5b-bam-umoe-wikitext2

tahamajs · Kit

Swaps 18 of the 24 attention layers in Qwen2.5-0.5B for a mixture-of-experts attention block, then distills it on WikiText-2. A research checkpoint for studyin…

Bielik-11B-v3.1-DFlash2

speakleash · Kit

Pairs with the Bielik-11B-v3.1-Instruct model as a draft model for speculative decoding in SGLang or vLLM. It is not a standalone language model.

Bielik-11B-v3.1-DFlash

speakleash · Kit

Serves as the DFlash draft model that pairs with Bielik-11B-v3.1-Instruct for speculative decoding in SGLang or vLLM. It is not a standalone language model. Fo…

Beam-1.0-501B-A23B-NVFP4

reflection · Kit

Reads and writes text with a 1M-token context, built for coding, agent tool use and math reasoning, as a 501B-parameter mixture-of-experts model in NVFP4 form.…

Flint NVFP4 GGUF

RecursiveSI · Kit

A 4-bit NVFP4 copy of the Recursive Flint text model as one GGUF file, built for NVIDIA GPUs through llama.cpp. For developers running a large local model with…

Kimi-K3.1-Dflash2-Preview

RadixArk · Kit

Speeds up Kimi-K3.1-Pro serving by drafting blocks of tokens that the main model checks in one pass. A draft model for SGLang users, used alongside the target…

Qwen3Guard-Gen-0.6B

Qwen · Kit

A small safety moderation model that labels a prompt or a model reply as safe, controversial or unsafe and names the risk categories, in 119 languages. Suits d…

Qwen3-1.7B-GGUF

Qwen · Kit

Gives you the small Qwen3 1.7B chat model as a q8_0 GGUF file for llama.cpp, with a switch between thinking and non-thinking replies. For people who want a lig…

Qwen3-1.7B-Base

Qwen · Kit

Continues text and code as a 1.7B base language model pre-trained on 119 languages. For developers who want a small model to fine-tune or test.