4-bit DWQ Open on Hugging Face
Parameters
73B
Weights (est.)
≈ 40.9 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/Kimi-Dev-72B-4bit-DWQ --prompt "Hello"
Details
- Base model
- moonshotai/Kimi-Dev-72B (quantized)
- Vendor
- Moonshot · Kimi
- Task
- Text generation
- Quantisation
- 4-bit DWQ
- Licence
- mit
- Downloads
- 1.8K in the last 30 days · 36K all time · 22 likes
- Published
- 2025-07-12 · updated 2025-07-12 (1y ago)
- Tags
- qwen2, code, swebench, software, issue-resolving
Other MLX builds of moonshotai/Kimi-Dev-72B
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| Kimi-Dev-72B-4bit-DWQ (this one) | 4-bit DWQ | ≈ 40.9 GB | 48 GB+ | 1.8K |
| Kimi-Dev-72B-4bit | 4-bit | ≈ 40.9 GB | 48 GB+ | 207 |
| Kimi-Dev-72B-5bit | 5-bit | ≈ 50.0 GB | 64 GB+ | 154 |
| Kimi-Dev-72B-6bit | 6-bit | ≈ 59.1 GB | 96 GB+ | 110 |
| Kimi-Dev-72B-8bit | 8-bit | ≈ 77.3 GB | 96 GB+ | 150 |