DeepSeek-V3-4bit
mlx-community/DeepSeek-V3-4bit
Uncategorised · mlx
4-bit Open on Hugging Face
Parameters
671B
Weights (est.)
≈ 378 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.
Details
- Base model
- deepseek-ai/DeepSeek-V3 (quantized) · DeepSeek V3 on the radar →
- Vendor
- DeepSeek
- Task
- Uncategorised
- Quantisation
- 4-bit
- Licence
- —
- Downloads
- 294 in the last 30 days · 306K all time · 10 likes
- Published
- 2025-01-07 · updated 2025-01-07 (1y ago)
- Tags
- deepseek_v3, custom_code
Other MLX builds of deepseek-ai/DeepSeek-V3
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| DeepSeek-V3-3bit | 3-bit | ≈ 294 GB | 512 GB+ | 78 |
| DeepSeek-V3-3bit-bf16 | 3-bit | ≈ 294 GB | 512 GB+ | 58 |
| DeepSeek-V3-4bit (this one) | 4-bit | ≈ 378 GB | 512 GB+ | 294 |