4-bit Open on Hugging Face
Parameters
35B
Weights (est.)
≈ 20.4 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.
Run it
With mlx-vlm on an Apple silicon Mac:
pip install mlx-vlmpython -m mlx_vlm.generate --model mlx-community/Qwopus3.6-35B-A3B-Coder-4bit --image photo.jpg --prompt "Describe this image"
Details
- Base model
- Jackrong/Qwopus3.6-35B-A3B-Coder (quantized)
- Vendor
- Jackrong
- Task
- Vision + text
- Quantisation
- 4-bit
- Licence
- apache-2.0
- Downloads
- 111 in the last 30 days · 1.9K all time · 3 likes
- Published
- 2026-06-30 · updated 2026-06-30 (4mo ago)
- Languages
- en, zh, es, ru, ja
- Tags
- qwen3_5_moe, qwen3_6, coder, agent, tool-use, function-calling, long-context, vision, video, multimodal, 4bit
Other MLX builds of Jackrong/Qwopus3.6-35B-A3B-Coder
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| Qwopus3.6-35B-A3B-Coder-4bit (this one) | 4-bit | ≈ 20.4 GB | 32 GB+ | 111 |
| Qwopus3.6-35B-A3B-Coder-6bit | 6-bit | ≈ 29.1 GB | 48 GB+ | 119 |
| Qwopus3.6-35B-A3B-Coder-8bit | 8-bit | ≈ 37.7 GB | 48 GB+ | 84 |
| Qwopus3.6-35B-A3B-Coder-bf16 | bf16 | ≈ 70.2 GB | 96 GB+ | 44 |