Edit Models filters

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

2,972

Full-text search

Active filters: 3-bit

goooop/UI-Venus-Ground-72B-3bit-GPTQ

69B • Updated Sep 16, 2025

beezu/Behemoth-ReduX-123B-v1-MLX-3Bit

Text Generation • 123B • Updated Sep 16, 2025 • 4

NexVeridian/Qwen3-Next-80B-A3B-Thinking-3bit

Text Generation • 80B • Updated Dec 25, 2025 • 86 • 2

NexVeridian/Ling-flash-2.0-3bit

Text Generation • 103B • Updated Sep 19, 2025 • 8 • 1

tensorbanana/vibevoice-7b-exl3-3bit

Updated Sep 19, 2025

Wwayu/Behemoth-ReduX-123B-v1-mlx-3Bit

Updated Sep 19, 2025 • 4

mlx-community/Ling-mini-2.0-3bit

Text Generation • 16B • Updated Sep 21, 2025 • 2

mrtoots/unsloth-DeepSeek-V3.1-Terminus-mlx-3Bit

Text Generation • 671B • Updated Sep 23, 2025 • 43 • 1

NexVeridian/KAT-Dev-3bit

Text Generation • 33B • Updated Sep 26, 2025 • 3

NexVeridian/Falcon-H1-34B-Instruct-3bit

Text Generation • 34B • Updated Sep 26, 2025 • 5

cs2764/Kimi-K2-Instruct-0905-mlx-3Bit-gs32

Text Generation • 1T • Updated Sep 28, 2025 • 86 • 1

mlx-community/Ring-1T-preview-3bit

Text Generation • Updated Sep 29, 2025 • 8 • 1

mrtoots/unsloth-GLM-4.6-mlx-3Bit

Text Generation • 353B • Updated Oct 1, 2025 • 26

zerofata/MS3.2-PaintedFantasy-Visage-v4-34b-exl3-3bpw

7B • Updated Oct 2, 2025

mlx-community/Apriel-1.5-15b-Thinker-3bit-MLX

Image-Text-to-Text • Updated Oct 3, 2025 • 4

NexVeridian/granite-4.0-micro-3bit

Text Generation • 0.4B • Updated Oct 28, 2025 • 8

mlx-community/granite-4.0-h-tiny-3bit-MLX

Text Generation • 0.9B • Updated Oct 3, 2025 • 83 • 2

Wwayu/Llama-3_1-Nemotron-Ultra-253B-CPT-v1-mlx-3Bit

Text Generation • Updated Oct 6, 2025 • 20

Wwayu/Monstral-123B-v2-mlx-3Bit

Text Generation • Updated Oct 6, 2025 • 9

mlx-community/LFM2-8B-A1B-3bit-MLX

Text Generation • 1B • Updated Oct 8, 2025 • 48 • 1

mlx-community/Qwen3-VL-30B-A3B-Instruct-3bit

Image-Text-to-Text • Updated Oct 11, 2025 • 41

mlx-community/Qwen3-VL-235B-A22B-Instruct-3bit

Updated Oct 13, 2025 • 203 • 2

mlx-community/Qwen3-VL-30B-A3B-Thinking-3bit

Image-Text-to-Text • Updated Oct 14, 2025 • 30 • 1

mlx-community/Qwen3-VL-235B-A22B-Thinking-3bit

Updated Oct 14, 2025 • 105

mlx-community/Qwen3-VL-4B-Instruct-3bit

Image-Text-to-Text • Updated Oct 14, 2025 • 652 • 2

mlx-community/Qwen3-VL-4B-Thinking-3bit

Image-Text-to-Text • Updated Oct 14, 2025 • 13

mlx-community/Qwen3-VL-8B-Instruct-3bit

Image-Text-to-Text • Updated Oct 14, 2025 • 21

mlx-community/Qwen3-VL-8B-Thinking-3bit

Image-Text-to-Text • Updated Oct 14, 2025 • 7

bylukeio/dolphin-2.9.1-llama-3-70b-exl3-3.0bpw

14B • Updated Oct 16, 2025 • 1

mlx-community/Qwen3-VL-2B-Instruct-3bit

Image-Text-to-Text • Updated Oct 21, 2025 • 66