DeepSeek-V3.2-Speciale
by deepseek-ai
685B params · text-generation · 710 likes · 2.2k downloads
DeepSeek-V3.2-Speciale is a 685B parameter model. At Q4 quantization it requires 343GB of VRAM. It requires a GPU with at least 343GB of VRAM.
Inference providers
| Provider | $/1M in | $/1M out | Throughput |
|---|---|---|---|
| Featherless |