AI projects from Hugging Face

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…

DeepSeek-V4.1-Flash-NVFP4

nvidia · Kit

Reads text and images and writes text, as a smaller NVFP4 copy of DeepSeek-V4.1-Flash made by NVIDIA. For developers deploying agents, chatbots and retrieval s…

DeepSeek-V4.1-Flash-1017-oQ4e-ngram-mtp

mlx-community · Kit

A mixed-precision MLX copy of DeepSeek-V4.1-Flash-1017 that keeps the Engram tables at FP8. Made for people with hundreds of GB of memory who want to run the m…

LongCap-35B-A3B-FP8

JinchuanTian · Kit

Turns recordings up to about two hours long into a timeline of speech, music and sound events with start and end times, and also transcribes speech with speake…

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…

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…

Kvark-Sparkle-1.0-27B

Egzakta · Kit

Reasons over images and text with fewer thinking tokens than its base Qwen3.8-27B, so answers arrive in about half the time at similar accuracy, per its card.…

GigaChat3.5-432B-A28B

ai-sage · Kit

Generates text in Russian and English for chat, code, reasoning and tool use. A 432B Mixture-of-Experts model with 28B active parameters, aimed at teams that h…

Occamy-1.0

Accio-Lab · Kit

An open 35B image and text model from Accio-Lab, based on Qwen3.6-35B-A3B, in BF16, GGUF, FP8, NVFP4 and MLX formats. For teams that serve a large model.

DeepSeek-V4-Pro

deepseek-ai · Kit

Generates text with a 1.6T-parameter Mixture-of-Experts model that activates 49B per token and reads up to one million tokens. A DeepSeek preview for teams tha…

DeepSeek-V3.2

deepseek-ai · Kit

A 685B open reasoning model from DeepSeek with sparse attention for long context and a chat template that lets it think while it calls tools. For teams that ru…

FLUX.1-schnell for ComfyUI

Comfy-Org · Kit

Repackaged FLUX.1-schnell checkpoints for ComfyUI that turn a text prompt into an image, with an FP8 file that runs faster and uses less memory. For ComfyUI us…

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…

Kolibri-1

Aleph-Alpha · Kit

Reasons and calls tools in German and English, with a context window of more than a million tokens. An open 78B mixture-of-experts model from Aleph Alpha that…

Qwen3.6-35B-A3B-FP8

Qwen · Kit

Reads text and images and writes text, as an FP8 copy of Qwen3.6-35B-A3B with 3B active parameters. For developers who run coding agents and want a smaller dow…

ttf-Qwen3.8-Flash-Next-GGUF

oguzeldereli · Kit

Runs Qwen3.8-Flash-Next, a 180B mixture-of-experts model squeezed to ternary weights, from one 40.4 GB GGUF file that is 4.6 times smaller than the FP8 release…

DeepSeek-V4.1-Flash-1017-NVFP4

nvidia · Kit

NVIDIA's NVFP4 quantized copy of DeepSeek AI's DeepSeek-V4.1-Flash-1017, a huge multimodal mixture-of-experts model for NVIDIA Blackwell GPUs.

Ling-3.1-flash

inclusionAI · Kit

Handles complex agent, search, office and coding work with 560B total and 25B active parameters and a 1M-token context. Serving examples use SGLang on multi-GP…

DeepSeek-V4.1-Flash-1017-Sushi-STQ-1.75bpw

beamster · Kit

Runs a 261B DeepSeek V4.1 Flash model packed to about 1.75 bits per weight for the sushi engine on Apple Silicon Macs, with image input and up to 1,048,576 tok…

Qwen3.8-27B NVFP4

nvidia · Kit

NVIDIA's 4-bit NVFP4 build of Alibaba's Qwen3.8-27B, made with Model Optimizer for Blackwell GPUs, taking text, image and video in and giving text back.