Edit Models filters

Model Tree

Apps

Docker Model Runner

Inference Providers

OVHcloud AI Endpoints

HF Inference API

Misc

Inference Endpoints

text-generation-inference

Eval Results (legacy)

text-embeddings-inference

4-bit precision

8-bit precision

Mixture of Experts

Carbon Emissions

Models

2,620

Base only

Active filters: 5-bit

zviratko/Qwen3.6-35B-A3B-oQ5-BF16

Image-Text-to-Text • 7B • Updated Apr 18 • 83

Xartorx/gemma-4-E4B-it-heretic-oQ5

2B • Updated Apr 17 • 60

Xartorx/gemma-4-31B-it-heretic-oQ5

6B • Updated Apr 17 • 38

Brooooooklyn/Qwen3.6-35B-A3B-UD-Q5_K_XL-mlx

Text Generation • 8B • Updated 22 days ago • 622 • 2

Outlier-Ai/Outlier-Lite-7B-GGUF

Text Generation • 8B • Updated May 5 • 61

Outlier-Ai/Outlier-Compact-14B-GGUF

Text Generation • 15B • Updated May 5 • 56 • 1

Outlier-Ai/Outlier-Max-32B-GGUF

Text Generation • 33B • Updated May 5 • 85 • 1

Xartorx/Qwen3.6-35B-A3B-heretic-oQ5

7B • Updated Apr 18 • 45

zecanard/gemma-4-E4B-it-ultra-uncensored-heretic-MLX-5bit-int5-affine

Any-to-Any • 2B • Updated 15 days ago • 701 • 1

zecanard/gemma-4-26B-A4B-it-uncensored-heretic-ara-MLX-5bit-int5-affine

Image-Text-to-Text • 6B • Updated 15 days ago • 512 • 1

zecanard/gemma-4-31b-it-uncensored-heretic-ara-MLX-5bit-int5-affine

Image-Text-to-Text • 9B • Updated 15 days ago • 428 • 1

nabi-chan/Qwen3.6-35B-A3B-Claude-4.6-Opus-Reasoning-Distilled-MLX-5bit

Image-Text-to-Text • 35B • Updated Apr 20 • 198

deepsweet/Qwen3.6-35B-A3B-MLX-oQ5-FP16

Text Generation • 7B • Updated 27 days ago • 507 • 1

beezu/G4-MeroMero-26B-A4B-mlx-5bit-gs32

Text Generation • 25B • Updated Apr 20 • 33

splats/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled-oQ5e

7B • Updated Apr 29 • 268

hzchng/GLM-4.7-Flash-oQ5

Text Generation • 6B • Updated Apr 21 • 192

aimeri/spoomplesmaxx-gemma4-31B-1200-mlx-5bit

Image-Text-to-Text • 8B • Updated Apr 21 • 49

cpral/Hermes-4-405B-exl3-5bpw

Text Generation • 129B • Updated Apr 22 • 3

mlx-community/Qwen3.6-27B-5bit

Image-Text-to-Text • 6B • Updated Apr 22 • 594 • 1

NexVeridian/Qwen3.6-27B-5bit

Text Generation • 27B • Updated May 1 • 281 • 1

TheCluster/Qwen3.6-27B-MLX-mixed-5.6bit

Image-Text-to-Text • 28B • Updated Apr 22 • 71 • 1

qurk41/Qwen3.6-27B-mlx-5Bit

Image-Text-to-Text • 27B • Updated Apr 23 • 69

AntimatterAI/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-MLX-5bit

Text Generation • 35B • Updated Apr 23 • 750 • 2

deepsweet/Qwen3.6-27B-MLX-oQ5-FP16

Text Generation • 5B • Updated 19 days ago • 1.16k • 1

mlx-community/sapiens2-seg-0.4b-5bit

Image-to-Image • 86.3M • Updated Apr 24 • 27

mlx-community/DeepSeek-V4-Flash-5bit

Text Generation • 284B • Updated Apr 25 • 1k

Brooooooklyn/Qwen3.6-27B-UD-Q5_K_XL-mlx

Text Generation • 8B • Updated 22 days ago • 858 • 2

blockblockblock/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled-exl3-5.0bpw

Text Generation • 12B • Updated 6 days ago • 160 • 1

splats/NVIDIA-Nemotron-3-Nano-30B-A3B-oQ5e

6B • Updated Apr 29 • 22

splats/Qwen3.6-27B-oQ5e

6B • Updated Apr 29 • 59