@cf/meta/llama-3.1-8b-instruct-fp8
Streams a reply to a ~20-word prompt, capped at 100 tokens; latency is the full reply.
5.02s?
Last Update53.38 s ago
Success (24h)100.0%
Predicted~4.82 s
Streams a reply to a ~20-word prompt, capped at 100 tokens; latency is the full reply.