Qwen3-8B-4bit

mlx-community

mlx-community/Qwen3-8B-4bit

GenerationOpen weights

View on Hugging Face ↗

Metrics

Downloads

33,163

last 30 days

Hub likes

20

Parameters

8.2B

published total

How it compares in Generation

SizeQwen3-8B-4bit sits in 1-10B — larger than 52% of the 1001 models in this category with a published size.

<1B87

1-10B476

10-100B338

>100B100

Details

Model ID: mlx-community/Qwen3-8B-4bit
Developer: mlx-community
Category: Generation
Access: Open weights
License: Not published
Source: Hugging Face
Data provenance: Catalogue listing — only the fields the source publishes are shown.
Link: https://huggingface.co/mlx-community/Qwen3-8B-4bit

More from mlx-community

Llama-3.1-8B-Instruct-4bitmlx-community/Llama-3.1-8B-Instruct-4bitGeneration Qwen3-30B-A3B-Instruct-2507-4bitmlx-community/Qwen3-30B-A3B-Instruct-2507-4bitGeneration Qwen3-0.6B-4bitmlx-community/Qwen3-0.6B-4bitGeneration Qwen3-4B-Instruct-2507-4bitmlx-community/Qwen3-4B-Instruct-2507-4bitGeneration all-MiniLM-L6-v2-4bitmlx-community/all-MiniLM-L6-v2-4bitEmbedding

Other Generation models

Qwen3-0.6BQwen/Qwen3-0.6BGeneration gpt2openai-community/gpt2Generation Qwen3-8BQwen/Qwen3-8BGeneration Qwen3.6-35B-A3B-NVFP4nvidia/Qwen3.6-35B-A3B-NVFP4Generation opt-125mfacebook/opt-125mGeneration OTel-2.0-LLM-31B-ITfarbodtavakkoli/OTel-2.0-LLM-31B-ITGeneration