4-bit Open on Hugging Face
Parameters
7.0B
Weights (est.)
≈ 8.2 GB
Mac memory (est.)
16 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.
Run it
With mlx-vlm on an Apple silicon Mac:
pip install mlx-vlmpython -m mlx_vlm.generate --model mlx-community/Qwen3.5-35B-A3B-GPTQ-Int4 --image photo.jpg --prompt "Describe this image"
Details
- Base model
- Qwen/Qwen3.5-35B-A3B (quantized)
- Vendor
- Qwen
- Task
- Vision + text
- Quantisation
- 4-bit
- Licence
- apache-2.0
- Downloads
- 36 in the last 30 days · 769 all time · 4 likes
- Published
- 2026-03-03 · updated 2026-03-03 (8mo ago)
- Tags
- qwen3_5_moe
Other MLX builds of Qwen/Qwen3.5-35B-A3B
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| Qwen3.5-35B-A3B-GPTQ-Int4 (this one) | 4-bit | ≈ 8.2 GB | 16 GB+ | 36 |
| Qwen3.5-35B-A3B-OptiQ-4bit | 4-bit | ≈ 20.4 GB | 32 GB+ | 621 |