Qwen2.5-Omni-3B-Thinker-4bit
mlx-community/Qwen2.5-Omni-3B-Thinker-4bit
Uncategorised · mlx
4-bit Open on Hugging Face
Parameters
—
Weights (est.)
—
Mac memory (est.)
—
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
- Qwen/Qwen2.5-Omni-3B (finetune)
- Vendor
- Qwen
- Task
- Uncategorised
- Quantisation
- 4-bit
- Licence
- qwen-research
- Downloads
- 477 in the last 30 days · 477 all time · 1 likes
- Published
- 2026-10-18 · updated 2026-11-02 (9d ago)
- Tags
- qwen2_5_omni_thinker_encoder, mlx-swift, qwen2.5-omni
Other MLX builds of Qwen/Qwen2.5-Omni-3B
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| Qwen2.5-Omni-3B-Thinker-4bit (this one) | 4-bit | — | — | 477 |
| Qwen2.5-Omni-3B-Thinker-8bit | 8-bit | — | — | 426 |
| Qwen2.5-Omni-3B-Thinker-bf16 | bf16 | — | — | 277 |