Llama-3.1-8B-Instruct
by meta-llama
text-generation · 5.5k likes · 7.4M downloads
Inference providers
| Provider | $/1M in | $/1M out | Throughput |
|---|---|---|---|
| Novita | 55 tok/s | ||
| Cerebras | 547 tok/s | ||
| SambaNova | 221 tok/s | ||
| Nscale | 59 tok/s | ||
| Featherless | |||
| Scaleway | 131 tok/s | ||
| OVHcloud | 44 tok/s |