Loading…
Loading…
Models / DeepSeek-R1-Distill-Qwen
4 models (1.5B to 32B) · ↓ 2.4M downloads a month · from $0.09/h on RTX 3060 right now. Each model's versions do the same job; quantized ones (AWQ, FP8, 4-bit) need less GPU memory and run on cheaper machines.
| Version | Runtime | Weights | GPU memory | Cheapest machine now |
|---|---|---|---|---|
| Originaldeepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B | vLLM | 3.5 GB | 6.4 GB | $0.10/h RTX 3060 |
| unsloth bnb 4bit (unsloth)unsloth/DeepSeek-R1-Distill-Qwen-1.5B-unsloth-bnb-4bit | vLLM | 1.8 GB | 4.5 GB | $0.10/h RTX 3060 |
| Version | Runtime | Weights | GPU memory | Cheapest machine now |
|---|---|---|---|---|
| Originaldeepseek-ai/DeepSeek-R1-Distill-Qwen-7B | vLLM | 15 GB | 19.7 GB | $0.18/h 2x RTX 3060 |
| ONNX WebGPU (danyalmalik)danyalmalik/DeepSeek-R1-Distill-Qwen-7B-ONNX-WebGPU | ONNX Runtime GenAI | 5.2 GB | 8 GB | $0.09/h RTX 3060 |
| Version | Runtime | Weights | GPU memory | Cheapest machine now |
|---|---|---|---|---|
| Originaldeepseek-ai/DeepSeek-R1-Distill-Qwen-14B | vLLM | 30 GB | 36.8 GB | $0.45/h Nvidia A40 |
| unsloth bnb 4bit (unsloth)unsloth/DeepSeek-R1-Distill-Qwen-14B-unsloth-bnb-4bit | vLLM | 14 GB | 19.9 GB | $0.18/h 2x RTX 3060 |
| Version | Runtime | Weights | GPU memory | Cheapest machine now |
|---|---|---|---|---|
| Originaldeepseek-ai/DeepSeek-R1-Distill-Qwen-32B | vLLM | 66 GB | 77.4 GB | $0.89/h 2x Nvidia A40 |
| quantized.w4a16 (RedHatAI)RedHatAI/DeepSeek-R1-Distill-Qwen-32B-quantized.w4a16 | vLLM | 19 GB | 25.9 GB | $0.34/h 2x RTX 5060 Ti |
Model details come from Hugging Face and are refreshed daily; prices follow the live offers. GPU memory is GridPup's estimate: the weights, room for an 8,192-token conversation (chat models) and the runtime's own memory. Large models are split across the GPUs of one machine ("4x RTX 4090").