Skip to content

Qwen3-Omni-30B-A3B-Instruct-5bit

mlx-community/Qwen3-Omni-30B-A3B-Instruct-5bit
Any to any · transformers
5-bit Open on Hugging Face
Parameters
35B
Weights (est.)
≈ 26.1 GB
Mac memory (est.)
32 GB+

Size is estimated from the parameter count and quantisation. Memory allows a fifth extra for context plus 2 GB for the system; long contexts need more.

Details

Base model
—
Vendor
—
Task
Any to any
Quantisation
5-bit
Licence
apache-2.0
Downloads
103 in the last 30 days · 548 all time · 1 likes
Published
2025-12-24 · updated 2025-12-24 (10mo ago)
Languages
en
Tags
qwen3_omni_moe, text-to-audio, multimodal