DeepSeek-V3.1
by deepseek-ai
685B params · text-generation · 818 likes · 149.8k downloads
DeepSeek-V3.1 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 | 36 tok/s | ||
| Together AI | 40 tok/s | ||
| Fireworks | 79 tok/s |