AI projects from Hugging Face

Qwen3.6-35B-A3B-NVFP4-Fast

unsloth · Kit

Serves Qwen3.6 35B A3B in a fast NVFP4 build by Unsloth for vLLM on NVIDIA GPUs. The card says it has 1.79x the throughput of other NVFP4 builds and fits a 32…

Ornith-1.5-122B-NVFP4-DFlash2-RTX-Spark

Sherlock-Comms · Kit

Serves the 122B Ornith 1.5 model through vLLM with DFlash2 speculative decoding, using an unquantized output head. Made for RTX Spark laptops with 128 GB of me…

Qwen3.8-27B-QUASAR-NVFP4

QUASAR-QAT · Kit

Runs Qwen3.8-27B in 4-bit NVFP4 at 19.7 GB, trained with the QUASAR method to stay close to the full BF16 model. For people serving it with vLLM on an NVIDIA B…

DeepSeek-V4.1-Flash-1017-EXL3-franken-v100

philbert440 · Kit

Runs DeepSeek V4.1 Flash at its full 1M-token context on eight Tesla V100 32 GB cards, using an EXL3 expert pack and an SM70 vLLM build. For owners of such ser…

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…

Leanstral 1.5 119B A6B

mistralai · Kit

An open code-agent model from Mistral for the Lean 4 proof assistant. It proves theorems and fixes Lean code, takes text and images, and runs through the Mistr…

Qwen3.8-27B-NVFP4 Deployment Edition

IteraCompute · Kit

Serves Qwen3.8-27B in NVFP4 on one RTX 5090 with vLLM, with a checksum-verified download, FP8 KV cache, tool calls and reasoning support. For developers self-h…

Qwen3.6-35B-A3B-2Bit-GSQ

ISTA-DASLab · Kit

A 2-bit quantized copy of Qwen3.6-35B-A3B made with GSQ, a Gumbel-Softmax method, that keeps most reasoning and coding ability at a much smaller memory footpri…

KVARK Sparkle 1.0 (27B) FP8

Egzakta · Kit

Runs a 27B model that reads images and text, in FP8 for vLLM. It reasons with far fewer tokens than a Qwen model of the same size. Made for people who host the…

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…

Qwen3.8-27B-NVFP4-DGX-SPARK

autotrust · Kit

Speeds up Qwen3.8-27B NVFP4 decoding about 3.9 times on a DGX Spark, using the same weights and a tuned speculative-decoding setup. For teams serving it with v…

OvisOCR2

ATH-MaaS · Kit

Document parsing model that reads a page image and writes Markdown in reading order, covering text, formulas and tables. About 0.8B parameters, run through vLL…

Qwen3.8-27B-Quark-AWQ-MXFP4

amd · Kit

Runs Qwen3.8-27B as a smaller MXFP4-quantized copy made with AMD Quark and AWQ, served through vLLM. Made for developers who want a compressed 27B vision-langu…

MiMo-V2.6-Flash-RL-NVFP4

primitive-ai · Kit

Serves Xiaomi's MiMo-V2.6-Flash-RL as an NVFP4 build for Blackwell GPUs, with the release's exact expert values and more throughput on two 96 GB cards. For peo…

GLM-5.3-Flash EXL3 3.05bpw

albucino · Kit

Runs GLM-5.3-Flash locally on two RTX 3090 cards with 128 GB of RAM and a 262,144-token context, using a verified 3.05 bpw EXL3 quantization. For people hostin…

DuplexJev-4B-Para

adventists-ai · Kit

Takes speech and text in, answers in text, and judges when a speaker has finished talking. Built for voice-agent developers who want a small audio model that a…

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…

Laguna XS 2.1

poolside · Kit

Writes code and works through long coding tasks with tool calls, using a 33B mixture-of-experts model that activates 3B parameters per token. For developers wh…

gpt-oss-safeguard-20b

openai · Kit

Classifies text against a safety policy you write and shows its reasoning. For trust and safety teams filtering model inputs and outputs, labeling content onli…

gpt-oss-safeguard-120b

openai · Kit

Sorts text against a safety policy that you write, and shows its reasoning for each decision. It suits trust and safety teams that filter or label content.

Comet 60B

MultiverseComputingCAI · Kit

A 61.1B multimodal model from Multiverse Computing, a compressed version of NVIDIA's Nemotron 3.5 Super that takes text, image and video and keeps about 12B pa…

Voxtral 4B TTS 2603

mistralai · Kit

An open-weights text-to-speech model from Mistral with 20 preset voices in nine languages, streaming output and low latency. Made for developers who build voic…

KAT-Coder-V2.5-Dev

Kwaipilot · Kit

An open-weight coding model from Kwaipilot, a mixture-of-experts with 35B total and 3B active parameters, tuned for agentic coding and fewer tool-call glitches…

Qwopus3.8-27B-Coder-Flash

Jackrong · Kit

Writes code, calls tools and works through software tasks as a coding agent. A 27.8B fine-tune of Qwen3.8-27B by Jackrong, trained on about 200,000 code and re…

Qwen3.8-27B-DFlash2 by incoai

incoai · Kit

Speeds up Qwen3.8-27B by drafting blocks of tokens that the main model then checks, with output unchanged. A 1.9B draft model for SGLang and vLLM servers, not…

MedErtas v0.1 31B LS

ErtasAI · Kit

Serves a medical-domain language model, a compressed Gemma 4 31B, on vLLM and NVIDIA Blackwell GPUs. Built for medical AI products that need fast, low-cost ans…

Qwen3.8-27B-AWQ-INT4

cyankiwi · Kit

A 4-bit AWQ quantization of Qwen3.8-27B by cyankiwi, a 27B vision-language model with thinking control. Weights are 21.02 GB and load in Transformers, vLLM or…

Ling-3.1-flash-1019

inclusionAI · Kit

Handles scientific and agentic tasks with 560B total and 25B active parameters and a 1M-token context, tuned further from Ling-3.1-flash. Serving examples use…

Qwen3.8-27B-Randean-MXFP4

flechin · Kit

A 27B reasoning model tuned to answer plainly instead of hedging, quantized to MXFP4 so vLLM can serve it on a single 32 GB GPU, for developers who run local r…

Jackrong_Qwopus3.8-27B-Coder-Flash-GGUF

bartowski · Kit

GGUF quantizations of Jackrong's Qwopus3.8-27B-Coder-Flash, made by bartowski with an importance matrix, in sizes from 17 GB to 55 GB. For running a 27B model…

Qwen3.5-35B-A3B

Qwen · Kit

A multimodal chat model that reads images and text, with 35B parameters of which 3B are active at a time. For developers who host their own large model with Tr…

Qwen Sharp Chat Templates

peculiar-ragdoll · Kit

Replaces the chat template of Qwen3.5, 3.6 and 3.8 models so they think less before answering and write tighter replies. For people running Qwen locally for co…

Mistral-7B-Instruct-v0.3

mistralai · Kit

A 7.2B open chat model from Mistral AI that follows instructions and can call functions you describe. It is fine-tuned from Mistral-7B-v0.3 and runs with mistr…

MedErtas v0.1 27B LS

ErtasAI · Kit

Open-weight medical language model squeezed to 22 GB, best at clinical calculations and facts from long patient records. For teams building medical AI products…

Qwen3.8-27B-DFlash2

z-lab · Kit

A draft model that speeds up Qwen3.8-27B by proposing a block of tokens for the main model to check. Not standalone. For people serving Qwen3.8-27B with SGLang…

d3-ultra

vllm-sr · Kit

Answers many questions about one text, image or video input at once, with a probability for each answer and no generated text. A 27B multimodal decision model…

Qwen3.6-35B-A3B-NVFP4

nvidia · Kit

A pre-quantized NVFP4 copy of Alibaba's Qwen3.6-35B-A3B, made by NVIDIA with Model Optimizer. It takes text, images and video, and runs on vLLM with Hopper or…

GLM-5.3-Flash-NVFP4

nvidia · Kit

Gives you NVIDIA's NVFP4 quantized copy of ZAI's GLM-5.3-Flash, a multimodal model for reasoning, coding and agent tasks. Meant for developers who deploy on Bl…

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…

DeepSeek-V4.1-Flash-EXL3-3bpw-2x-RTX-PRO-6000

diffbot · Kit

Serves a 3-bit compressed copy of DeepSeek-V4.1-Flash-1017 on two 96 GB RTX PRO 6000 Blackwell cards with vLLM, for developers who host a large coding and agen…

OvisOCR3

ATH-MaaS · Kit

Reads document images and returns text, structured JSON, Markdown with formulas and tables, key fields and figure captions from one 0.8B model. For developers…

Qwen3.8-27B-NVFP4

unsloth · Kit

A 4-bit NVFP4 copy of the Qwen3.8 27B vision-language model made by Unsloth, for serving with vLLM. For developers who want a dense model that reads images and…

OpenJev

openjev · Kit

Answers typed decisions about text, web pages and screenshots, picking a choice, a yes-or-no probability or a score from your own labels in one forward pass. F…

hs-decide-1-flash

hindsight-ai · Kit

Answers typed questions about a text state with a probability for every option in one pass, with no generated text, in eight languages. A 0.8B decision model f…

Qwopus3.8-27B-Coder-Flash-GGUF

Jackrong · Kit

Helps with coding and tool-using agent work as a GGUF fine-tune of Qwen3.8-27B, trained on about 200,000 code, agent and reasoning examples. For developers who…

gpt-oss-120b

openai · Kit

An open-weight OpenAI language model with 117B parameters, adjustable reasoning effort, visible chain of thought and tool use. Runs on one 80 GB GPU and ships…

Qwen-Fixed-Chat-Templates

froggeric · Kit

Swaps Qwen's official chat templates for one drop-in Jinja file that fixes rendering errors, cache invalidation, wasted tokens and agent stalls. For people who…

Qwen3.8-27B-FP8

Qwen · Kit

Handles text, images and video with FP8-quantized weights of Qwen3.8-27B, a 27B dense model with adjustable thinking. For developers serving it with transforme…

gpt-oss-20b

openai · Kit

Writes, reasons and calls tools from text prompts, in an open-weight 21B model from OpenAI that runs within 16 GB of memory. For developers who want a local or…