DeepSeek-R1-Distill-Llama-8B-6bit
mlx-community/DeepSeek-R1-Distill-Llama-8B-6bit
Uncategorised · mlx
6-bit Open on Hugging Face
Parameters
8.0B
Weights (est.)
≈ 6.5 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.
Details
- Base model
- deepseek-ai/DeepSeek-R1-Distill-Llama-8B (quantized)
- Vendor
- DeepSeek
- Task
- Uncategorised
- Quantisation
- 6-bit
- Licence
- —
- Downloads
- 62 in the last 30 days · 4.4K all time · 0 likes
- Published
- 2025-01-20 · updated 2025-02-26 (1y ago)
- Tags
- llama
Other MLX builds of deepseek-ai/DeepSeek-R1-Distill-Llama-8B
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| DeepSeek-R1-Distill-Llama-8B-3bit | 3-bit | ≈ 3.5 GB | 8 GB+ | 53 |
| DeepSeek-R1-Distill-Llama-8B-4bit | 4-bit | ≈ 4.5 GB | 8 GB+ | 809 |
| DeepSeek-R1-Distill-Llama-8B-4bit-mlx | 4-bit | ≈ 4.5 GB | 8 GB+ | 73 |
| DeepSeek-R1-Distill-Llama-8B-6bit (this one) | 6-bit | ≈ 6.5 GB | 16 GB+ | 62 |
| DeepSeek-R1-Distill-Llama-8B-8bit | 8-bit | ≈ 8.5 GB | 16 GB+ | 142 |
| DeepSeek-R1-Distill-Llama-8B-8bit-mlx | 8-bit | ≈ 8.5 GB | 16 GB+ | 53 |
| DeepSeek-R1-Distill-Llama-8B | — | ≈ 16.1 GB | 24 GB+ | 197 |
| DeepSeek-R1-Distill-Llama-8B-bf16 | bf16 | ≈ 16.1 GB | 24 GB+ | 67 |