DeepSeek-R1-Distill-Qwen-1.5B-bf16
mlx-community/DeepSeek-R1-Distill-Qwen-1.5B-bf16
Uncategorised · mlx
bf16 Open on Hugging Face
Parameters
1.8B
Weights (est.)
≈ 3.6 GB
Mac memory (est.)
8 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-Qwen-1.5B (finetune)
- Vendor
- DeepSeek
- Task
- Uncategorised
- Quantisation
- bf16
- Licence
- —
- Downloads
- 71 in the last 30 days · 6.4K all time · 1 likes
- Published
- 2025-01-20 · updated 2025-02-26 (1y ago)
- Tags
- qwen2
Other MLX builds of deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| DeepSeek-R1-Distill-Qwen-1.5B-3bit | 3-bit | ≈ 778 MB | 8 GB+ | 168 |
| DeepSeek-R1-Distill-Qwen-1.5B-4bit | 4-bit | ≈ 1000 MB | 8 GB+ | 2.9K |
| DeepSeek-R1-Distill-Qwen-1.5B-6bit | 6-bit | ≈ 1.4 GB | 8 GB+ | 89 |
| DeepSeek-R1-Distill-Qwen-1.5B-8bit | 8-bit | ≈ 1.9 GB | 8 GB+ | 755 |
| DeepSeek-R1-Distill-Qwen-1.5B-MLX-Q8 | 8-bit | ≈ 1.9 GB | 8 GB+ | 61 |
| deepseek-r1-distill-qwen-1.5b | — | ≈ 3.6 GB | 8 GB+ | 1.0K |
| DeepSeek-R1-Distill-Qwen-1.5B-chat-mlx-16bit | 16-bit | ≈ 3.6 GB | 8 GB+ | 542 |
| DeepSeek-R1-Distill-Qwen-1.5B-bf16 (this one) | bf16 | ≈ 3.6 GB | 8 GB+ | 71 |
| DeepSeek-R1-Distill-Qwen-1.5B-MLX | — | — | — | 0 |