Qwen3-Coder-480B-A35B-Instruct-4bit
mlx-community/Qwen3-Coder-480B-A35B-Instruct-4bit
Text generation · mlx
4-bit Open on Hugging Face
Parameters
480B
Weights (est.)
≈ 270 GB
Mac memory (est.)
512 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-lm on an Apple silicon Mac:
pip install mlx-lmmlx_lm.generate --model mlx-community/Qwen3-Coder-480B-A35B-Instruct-4bit --prompt "Hello"
Details
- Base model
- Qwen/Qwen3-Coder-480B-A35B-Instruct (quantized)
- Vendor
- Qwen
- Task
- Text generation
- Quantisation
- 4-bit
- Licence
- apache-2.0
- Downloads
- 914 in the last 30 days · 106K all time · 19 likes
- Published
- 2025-07-22 · updated 2025-07-22 (1y ago)
- Tags
- qwen3_moe
Other MLX builds of Qwen/Qwen3-Coder-480B-A35B-Instruct
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| Qwen3-Coder-480B-A35B-Instruct-4bit (this one) | 4-bit | ≈ 270 GB | 512 GB+ | 914 |
| Qwen3-Coder-480B-A35B-Instruct-8bit | 8-bit | ≈ 510 GB | > 512 GB | 591 |