DeepSeek-V4-Pro
by deepseek-ai
862B params · text-generation · 5.0k likes · 2.6M downloads
DeepSeek-V4-Pro is a 862B parameter model. At Q4 quantization it requires 431GB of VRAM. It requires a GPU with at least 431GB of VRAM.
Inference providers
| Provider | $/1M in | $/1M out | Throughput |
|---|---|---|---|
| Novita | 59 tok/s | ||
| Together AI | 57 tok/s | ||
| Fireworks | 47 tok/s | ||
| Featherless | |||
| deepinfra | 40 tok/s |