Qwen3-Coder-30B-A3B-Instruct-8bit-DWQ-lr5e-8
mlx-community/Qwen3-Coder-30B-A3B-Instruct-8bit-DWQ-lr5e-8
Text generation · mlx
8-bit DWQ Open on Hugging Face
Parameters
31B
Weights (est.)
≈ 32.4 GB
Mac memory (est.)
48 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-30B-A3B-Instruct-8bit-DWQ-lr5e-8 --prompt "Hello"
Details
- Base model
- Qwen/Qwen3-Coder-30B-A3B-Instruct (quantized)
- Vendor
- Qwen
- Task
- Text generation
- Quantisation
- 8-bit DWQ
- Licence
- apache-2.0
- Downloads
- 240 in the last 30 days · 2.3K all time · 2 likes
- Published
- 2025-08-01 · updated 2025-08-01 (1y ago)
- Tags
- qwen3_moe
Other MLX builds of Qwen/Qwen3-Coder-30B-A3B-Instruct
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| Qwen3-Coder-30B-A3B-Instruct-3bit | 3-bit | ≈ 13.4 GB | 24 GB+ | 1.1K |
| Qwen3-Coder-30B-A3B-Instruct-4bit | 4-bit | ≈ 17.2 GB | 24 GB+ | 19K |
| Qwen3-Coder-30B-A3B-Instruct-4bit-dwq-v2 | 4-bit DWQ | ≈ 17.2 GB | 24 GB+ | 1.1K |
| Qwen3-Coder-30B-A3B-Instruct-4bit-DWQ | 4-bit DWQ | ≈ 17.2 GB | 24 GB+ | 739 |
| Qwen3-Coder-30B-A3B-Instruct-5bit | 5-bit | ≈ 21.0 GB | 32 GB+ | 256 |
| Qwen3-Coder-30B-A3B-Instruct-6bit | 6-bit | ≈ 24.8 GB | 32 GB+ | 1.3K |
| Qwen3-Coder-30B-A3B-Instruct-6bit-DWQ-lr3e-7 | 6-bit DWQ | ≈ 24.8 GB | 32 GB+ | 610 |
| Qwen3-Coder-30B-A3B-Instruct-6bit-DWQ-lr9e-8 | 6-bit DWQ | ≈ 24.8 GB | 32 GB+ | 128 |
| Qwen3-Coder-30B-A3B-Instruct-8bit | 8-bit | ≈ 32.4 GB | 48 GB+ | 1.4K |
| Qwen3-Coder-30B-A3B-Instruct-8bit-DWQ-lr5e-8 (this one) | 8-bit DWQ | ≈ 32.4 GB | 48 GB+ | 240 |
| Qwen3-Coder-30B-A3B-Instruct-8bit-DWQ-lr9e8 | 8-bit DWQ | ≈ 32.4 GB | 48 GB+ | 193 |
| Qwen3-Coder-30B-A3B-Instruct-8bit-DWQ-lr2e7 | 8-bit DWQ | ≈ 32.4 GB | 48 GB+ | 180 |
| Qwen3-Coder-30B-A3B-Instruct-8bit-DWQ-lr4e7 | 8-bit DWQ | ≈ 32.4 GB | 48 GB+ | 141 |
| Qwen3-Coder-30B-A3B-Instruct-8bit-DWQ-lr1e-6 | 8-bit DWQ | ≈ 32.4 GB | 48 GB+ | 141 |
| Qwen3-Coder-30B-A3B-Instruct-bf16 | bf16 | ≈ 61.1 GB | 96 GB+ | 606 |