Edit Models filters

Apps

Docker Model Runner

Inference Providers

HF Inference API

Misc

Inference Endpoints

text-generation-inference

4-bit precision

8-bit precision

text-embeddings-inference

Carbon Emissions

Mixture of Experts

Models

2,811

Full-text search

Active filters: 3-bit

mlx-community/gemma-3n-E4B-it-3bit

Image-Text-to-Text • 2B • Updated 24 days ago • 66

mlx-community/gemma-3n-E4B-3bit

Image-Text-to-Text • 2B • Updated 24 days ago • 198

pcuenq/Hunyuan-7B-Instruct-tokenizer

Text Generation • Updated 23 days ago • 14

Kaipengm2/openvla_3bit

2B • Updated 23 days ago • 2

eewer/Qwen3-0.6B-3bit-GPTQ

0.2B • Updated 23 days ago • 24

Disya/ERNIE-4.5-21B-A3B-PT-exl3-3bpw

Text Generation • 4B • Updated 22 days ago • 21

mlx-community/SmolLM3-3B-3bit

Text Generation • 0.4B • Updated 22 days ago • 97 • 2

mlx-community/SmolLM3-3B-Base-3bit

Text Generation • 0.4B • Updated 22 days ago • 42

irish-quant/Qwen-Qwen3-0.6B-3bit

0.2B • Updated 22 days ago • 2

irish-quant/Qwen-Qwen3-1.7B-3bit

0.5B • Updated 22 days ago • 3

irish-quant/Qwen-Qwen3-14B-3bit

3B • Updated 22 days ago • 2

irish-quant/Qwen-Qwen3-32B-3bit

5B • Updated 22 days ago • 3

irish-quant/Qwen-Qwen3-4B-3bit

0.8B • Updated 22 days ago • 3

irish-quant/Qwen-Qwen3-8B-3bit

2B • Updated 22 days ago • 3

figodeng/DeepSeek-R1-Distill-Llama-70B-3bit

9B • Updated 20 days ago • 12

steampunque/Llama-3.3-70B-Instruct-Hybrid-GGUF

71B • Updated 19 days ago • 101

notname0192/dd

Image-Text-to-Text • 2B • Updated 18 days ago • 5

nightmedia/Polaris-4B-Preview-dwq3-mlx

Text Generation • 0.6B • Updated 17 days ago • 7

nafisabdkhan/DeepSeek-Coder-V2-Instruct-mlx-3Bit

30B • Updated 16 days ago • 427

Darkhn/M3.2-24B-Animus-V5.1-Pro-3.0bpw-h6-exl2

Updated 16 days ago • 2

elimelec1/Mistral-7B-Instruct-v0.3-mlx-3bit

Text Generation • 0.9B • Updated 16 days ago • 58

irish-quant/mistralai-Mistral-7B-Instruct-v0.3-3bit

1.0B • Updated 16 days ago • 1

irish-quant/mistralai-Mistral-7B-v0.3-3bit

1.0B • Updated 16 days ago • 1

NexVeridian/Qwen3-30B-A3B-3bit

Text Generation • 31B • Updated about 15 hours ago • 44

beezu/StrawberryLemonade-70B-v1.1-MLX-3Bit

Text Generation • 71B • Updated 13 days ago • 30

NexVeridian/Qwen3-32B-3bit

Text Generation • 33B • Updated 13 days ago • 14

NexVeridian/Qwen3-1.7B-3bit

Text Generation • 0.2B • Updated 12 days ago • 6

NexVeridian/Qwen3-4B-3bit

Text Generation • 0.5B • Updated 12 days ago • 4

NexVeridian/Qwen3-8B-3bit

Text Generation • 1B • Updated 12 days ago • 7

NexVeridian/Qwen3-14B-3bit

Text Generation • 15B • Updated 12 days ago • 8