DeepSeek-R1
by deepseek-ai
685B params · text-generation · 13.1k likes · 1.2M downloads
DeepSeek-R1 is a 685B parameter model. At Q4 quantization it requires 342GB of VRAM. It requires a GPU with at least 342GB of VRAM.
Inference providers
| Provider | $/1M in | $/1M out | Throughput |
|---|---|---|---|
| Novita | 40 tok/s | ||
| SambaNova | 187 tok/s | ||
| Hyperbolic | 117 tok/s | ||
| Together AI | 68 tok/s |