The fastest TheDrummer model is Rocinante 12B at 86 output tokens per second. UnslopNemo 12B (54 t/s) and Skyfall 36B V2 (32 t/s) round out the top three.
AI models ranked by output speed (tokens per second, p50). The fastest large language models for low-latency and high-throughput applications.
The fastest TheDrummer model is Rocinante 12B at 86 output tokens per second. UnslopNemo 12B (54 t/s) and Skyfall 36B V2 (32 t/s) round out the top three.
UnslopNemo 12B (54 t/s) is the closest alternative on this metric, followed by Skyfall 36B V2 (32 t/s). See the full ranking above for the tradeoffs.
modelgrep tracks 4 TheDrummer models with live benchmarks, speed, latency and per-provider pricing. 4 of them qualify for this ranking.