Edit Models filters

Model Tree

Apps

Docker Model Runner

Unsloth Desktop

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

2,924

Base only

Active filters: 5-bit

mlx-community/Nemotron-Cascade-2-30B-A3B-5bit

Text Generation • 32B • Updated Mar 20 • 32 • 1

mlx-community/MolmoPoint-8B-5bit

Image-Text-to-Text • 3B • Updated Mar 21 • 8

nyueki/Maginum-Cydoms-24B-mlx-5Bit

Text Generation • 24B • Updated Mar 22 • 15 • 1

beezu/Magistry-24B-v1.1-mlx-5bit-gs32

Text Generation • 24B • Updated Mar 22 • 21

beezu/Q3.5-BlueStar-v2-27B-mlx-5bit-gs32

Text Generation • 27B • Updated Mar 23 • 7

LiquidAI/LFM2.5-350M-MLX-5bit

Text Generation • 66.5M • Updated 20 days ago • 343 • 8

blockblockblock/Qwen3.5-9B-Claude-4.6-Opus-Reasoning-Distilled-v2-5bpw-exl3

Text Generation • 4B • Updated Mar 26 • 6

mlx-community/dots.mocr-5bit

Image-Text-to-Text • 2B • Updated Apr 3 • 10

mlx-community/sam3-5bit

0.2B • Updated Mar 28 • 8 • 1

groxaxo/Qwen3.5-27B-Writer-exl3-5bpw-hb8

Text Generation • 10B • Updated 11 days ago • 207

Brooooooklyn/Qwen3.5-35B-A3B-UD-Q5_K_XL-mlx

Text Generation • 8B • Updated Mar 29 • 143 • 2

Brooooooklyn/Qwen3.5-9B-UD-Q5_K_XL-mlx

Text Generation • 3B • Updated Mar 29 • 70

Brooooooklyn/Qwen3.5-27B-UD-Q5_K_XL-mlx

Text Generation • 8B • Updated Mar 29 • 32 • 1

mobbitxt/Anubis-Mini-8B-v1-oQ5

2B • Updated Mar 30 • 18

mlx-community/NVIDIA-Nemotron-3-Super-120B-A12B-5bit

Text Generation • 121B • Updated Mar 30 • 646 • 3

RepublicOfKorokke/GLM-4.7-Flash-REAP-23B-A3B-oQ5

Text Generation • 4B • Updated Mar 30 • 46

mlx-community/LongCat-AudioDiT-1B-5bit

Text-to-Speech • 0.4B • Updated Mar 31 • 6

mlx-community/LongCat-AudioDiT-3.5B-5bit

Text-to-Speech • 0.8B • Updated Mar 31 • 11

UnstableLlama/Qwen3.5-27B-earica-5.00bpw-exl3

10B • Updated Mar 31 • 3

matt-here/MLX-Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-v2-5bit

Text Generation • 27B • Updated Mar 31 • 46 • 1

mlx-community/granite-vision-3.2-2b-5bit

Image-Text-to-Text • 0.9B • Updated Apr 1 • 12

mlx-community/granite-4.0-3b-vision-5bit

Image-Text-to-Text • 1B • Updated Apr 1 • 21 • 1

himefei/Qwen3.5-35B-A3B-oQ5e

7B • Updated Apr 2 • 3

juanquivilla/sotto-cleanup-lfm25-350m-mlx-5bit

Text Generation • 66.5M • Updated May 7 • 107 • 2

matt-here/MLX-Qwopus3.5-27B-v3-5bit

Text Generation • 27B • Updated Apr 11 • 8

matt-here/MLX-Qwopus3.5-27B-v3-vision-5bit

Image-Text-to-Text • 6B • Updated Apr 11 • 7

mlx-community/Trinity-Large-Thinking-5bit

Text Generation • 399B • Updated Apr 2 • 25

mlx-community/gemma-4-31b-it-5bit

Image-Text-to-Text • 6B • Updated Jul 5 • 97 • 3

mlx-community/gemma-4-26b-a4b-it-5bit

Image-Text-to-Text • 5B • Updated Jul 5 • 205 • 3

mlx-community/gemma-4-e4b-it-5bit

Image-Text-to-Text • 2B • Updated Jul 6 • 76 • 1