cogito-671b-v2.1-FP8
by deepcogito
671B params · text-generation · 11 likes · 251 downloads
cogito-671b-v2.1-FP8 is a 671B parameter model. At Q4 quantization it requires 336GB of VRAM. It requires a GPU with at least 336GB of VRAM.
Inference providers
| Provider | $/1M in | $/1M out | Throughput |
|---|---|---|---|
| Together AI | 77 tok/s |