DeepSeek-Coder-V2-Lite-Instruct-4bit-AWQ
mlx-community/DeepSeek-Coder-V2-Lite-Instruct-4bit-AWQ
Text generation · mlx
4-bit Open on Hugging Face
Parameters
16B
Weights (est.)
≈ 8.8 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-lm on an Apple silicon Mac:
pip install mlx-lmmlx_lm.generate --model mlx-community/DeepSeek-Coder-V2-Lite-Instruct-4bit-AWQ --prompt "Hello"
Details
- Base model
- deepseek-ai/DeepSeek-Coder-V2-Lite-Instruct (finetune)
- Vendor
- DeepSeek
- Task
- Text generation
- Quantisation
- 4-bit
- Licence
- deepseek-license
- Downloads
- 276 in the last 30 days · 7.5K all time · 1 likes
- Published
- 2025-06-26 · updated 2025-06-27 (1y ago)
- Tags
- deepseek_v2, custom_code
Other MLX builds of deepseek-ai/DeepSeek-Coder-V2-Lite-Instruct
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| DeepSeek-Coder-V2-Lite-Instruct-4bit | 4-bit | ≈ 8.8 GB | 16 GB+ | 807 |
| DeepSeek-Coder-V2-Lite-Instruct-4bit-AWQ (this one) | 4-bit | ≈ 8.8 GB | 16 GB+ | 276 |
| DeepSeek-Coder-V2-Lite-Instruct-6bit | 6-bit | ≈ 12.8 GB | 24 GB+ | 278 |