Edit Models filters

Model Tree

Apps

Docker Model Runner

Inference Providers

OVHcloud AI Endpoints

HF Inference API

One-click Deployment

Inference Endpoints

Microsoft Foundry

Amazon SageMaker AI

Misc

text-generation-inference

Eval Results (legacy)

text-embeddings-inference

4-bit precision

8-bit precision

Mixture of Experts

Carbon Emissions

Models

215

Base only

Active filters: mxfp8

zianglih/DeepSeek-V3.2-6layer-last-1-bf16

Text Generation • 39B • Updated Apr 2 • 9

mlx-community/gemma-4-31b-it-mxfp8

Image-Text-to-Text • 9B • Updated 26 days ago • 803 • 9

mlx-community/gemma-4-26b-a4b-it-mxfp8

Image-Text-to-Text • 8B • Updated 26 days ago • 2.7k • 4

nightmedia/gemma-4-E2B-it-mxfp8-mlx

Any-to-Any • 2B • Updated Apr 15 • 11

nightmedia/gemma-4-E4B-it-mxfp8-mlx

Any-to-Any • 3B • Updated Apr 15 • 32 • 2

nightmedia/gemma-4-E4B-it-mxfp4-mlx

Any-to-Any • 2B • Updated Apr 15 • 39 • 1

nightmedia/gemma-4-31B-it-mxfp8-mlx

Image-Text-to-Text • 9B • Updated Apr 13 • 15

nightmedia/gemma-4-26B-A4B-it-mxfp8-mlx

Image-Text-to-Text • 8B • Updated Apr 13 • 14

rdtand/Qwen3.5-122B-A10B-PrismaQuant-4.75bit-vllm

Image-Text-to-Text • 72B • Updated Apr 21 • 1.29k • 19

nightmedia/gemma-4-E4B-it-The-DECKARD-HERETIC-UNCENSORED-Thinking-mxfp8-mlx

Any-to-Any • 3B • Updated Apr 13 • 85 • 1

nightmedia/gemma-4-E4B-it-The-DECKARD-V2-Strong-HERETIC-UNCENSORED-Thinking-mxfp8-mlx

Any-to-Any • 3B • Updated Apr 15 • 70 • 1

nightmedia/gemma-4-26B-A4B-cosine-slerp-mxfp8-mlx

Image-Text-to-Text • 8B • Updated Apr 13 • 12

nightmedia/gemma-4-E4B-it-The-DECKARD-V3-Expresso-HERETIC-UNCENSORED-Thinking-mxfp8-mlx

Any-to-Any • 3B • Updated Apr 15 • 141 • 2

nightmedia/gemma-4-E4B-it-The-DECKARD-Expresso-Universe-HERETIC-UNCENSORED-Thinking-mxfp8-mlx

Any-to-Any • 3B • Updated Apr 15 • 526 • 4

zianglih/DeepSeek-V3.2-MXFP8

Text Generation • 707B • Updated Apr 11 • 9

zianglih/DeepSeek-V3.2-MXFP8-RL

Text Generation • 707B • Updated Apr 11 • 13

nightmedia/gemma-4-E4B-it-Claude-Opus-4.5-HERETIC-UNCENSORED-Thinking-mxfp8-mlx

Any-to-Any • 3B • Updated Apr 13 • 136 • 1

nightmedia/gemma-4-E4B-it-Architect-Expresso-Universe-mxfp8-mlx

Any-to-Any • 3B • Updated Apr 13 • 22

nightmedia/gemma-4-E2B-it-qx86-hi-mlx

Any-to-Any • 2B • Updated Apr 15 • 8

TheCluster/Darwin-35B-A3B-Opus-MLX-mxfp8

Image-Text-to-Text • 35B • Updated Apr 15 • 51 • 11

TheCluster/Qwen3.6-35B-A3B-Heretic-MLX-mxfp8

Image-Text-to-Text • 35B • Updated Apr 25 • 128 • 2

rdtand/Qwen3.6-35B-A3B-PrismaQuant-4.75bit-vllm

Image-Text-to-Text • 21B • Updated Apr 21 • 100k • 34

cyburn/Qwen3.6-35B-A3B-PrismaQuant-4.9bit-vllm

Image-Text-to-Text • 21B • Updated Apr 22 • 65 • 4

rdtand/Qwen3.6-27B-PrismaQuant-5.5bit-vllm

Image-Text-to-Text • 18B • Updated Apr 22 • 61.2k • 27

LibraxisAI/Huihui4-48B-A4B-vmlx-mxfp8

Image-Text-to-Text • 14B • Updated May 11 • 16

TheCluster/Qwen3.6-27B-Heretic-MLX-mxfp8

Image-Text-to-Text • 28B • Updated Apr 25 • 53

LibraxisAI/Huihui-Qwen3.6-35B-A3B-Claude-4.7-Opus-abliterated-vmlx-mxfp8

Image-Text-to-Text • 10B • Updated May 12 • 275 • 1

sombra-x/GLM-5.1-REAP-Solidity-MXFP8

Text Generation • 381B • Updated Apr 27 • 150

cyburn/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled-PrismaQuant-4.75bit-vllm

Text Generation • 21B • Updated Apr 27 • 614 • 2

cyburn/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled-PrismaQuant-8bit-vllm

Text Generation • 27B • Updated Apr 28 • 469 • 2