DeepSeek-V3-0324
by deepseek-ai
685B params · text-generation · 3.1k likes · 289.1k downloads
DeepSeek-V3-0324 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 | 32 tok/s | ||
| SambaNova | 206 tok/s | ||
| Hyperbolic | 41 tok/s | ||
| Together AI | 31 tok/s |