3-bit Open on Hugging Face
Parameters
236B
Weights (est.)
≈ 103 GB
Mac memory (est.)
128 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-V2.5-1210-3bit --prompt "Hello"
Details
- Base model
- deepseek-ai/DeepSeek-V2.5-1210 (quantized)
- Vendor
- DeepSeek
- Task
- Text generation
- Quantisation
- 3-bit
- Licence
- deepseek
- Downloads
- 52 in the last 30 days · 998 all time · 2 likes
- Published
- 2024-12-11 · updated 2024-12-11 (1y ago)
- Tags
- deepseek_v2, custom_code
Other MLX builds of deepseek-ai/DeepSeek-V2.5-1210
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| DeepSeek-V2.5-1210-3bit (this one) | 3-bit | ≈ 103 GB | 128 GB+ | 52 |
| DeepSeek-V2.5-1210-3bit-32 | 3-bit | ≈ 103 GB | 128 GB+ | 36 |
| DeepSeek-V2.5-1210-4bit | 4-bit | ≈ 133 GB | 192 GB+ | 116 |