The fastest IBM model is Granite 4.1 8B at 118 output tokens per second. Granite 4.0 Micro (27 t/s) is next.
AI models ranked by output speed (tokens per second, p50). The fastest large language models for low-latency and high-throughput applications.
The fastest IBM model is Granite 4.1 8B at 118 output tokens per second. Granite 4.0 Micro (27 t/s) is next.
Granite 4.0 Micro (27 t/s) is the closest alternative on this metric. See the full ranking above for the tradeoffs.
modelgrep tracks 2 IBM models with live benchmarks, speed, latency and per-provider pricing, led on intelligence by Granite 4.1 8B. 2 of them qualify for this ranking.