Llama-3.1-405B
by meta-llama
406B params · text-generation · 977 likes · 299.9k downloads
Llama-3.1-405B is a 406B parameter model. At Q4 quantization it requires 203GB of VRAM. It requires a GPU with at least 203GB of VRAM.
Inference providers
| Provider | $/1M in | $/1M out | Throughput |
|---|---|---|---|
| Featherless |