DeepSeek-V3.1-Terminus
by deepseek-ai
685B params · text-generation · 363 likes · 11.3k downloads
DeepSeek-V3.1-Terminus 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 | 37 tok/s |