DeepSeek-V2.5-MLX-AQ4_1_64
mlx-community/DeepSeek-V2.5-MLX-AQ4_1_64
Uncategorised · mlx
4-bit Open on Hugging Face
Parameters
236B
Weights (est.)
≈ 133 GB
Mac memory (est.)
192 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-V2.5 (quantized)
- Vendor
- DeepSeek
- Task
- Uncategorised
- Quantisation
- 4-bit
- Licence
- deepseek
- Downloads
- 52 in the last 30 days · 958K all time · 2 likes
- Published
- 2024-09-07 · updated 2024-09-07 (2y ago)
- Tags
- deepseek_v2, custom_code