modelgrep

Fastest IBM Models

Quick answer · Updated June 2026

The fastest IBM model is Granite 4.1 8B at 118 output tokens per second. Granite 4.0 Micro (27 t/s) is next.

118 t/sSpeed
12.4Intelligence
$0.050Input /M
131KContext

AI models ranked by output speed (tokens per second, p50). The fastest large language models for low-latency and high-throughput applications.

  1. 1I
    granite-4.1-8b
    ToolsJSON12.4 intel · $0.050/M · 144ms ttft
    118 t/s
    Speed
  2. 2I
    granite-4.0-h-micro
    7.7 intel · $0.017/M · 301ms ttft
    27 t/s
    Speed

Frequently asked

What is the fastest IBM model?

The fastest IBM model is Granite 4.1 8B at 118 output tokens per second. Granite 4.0 Micro (27 t/s) is next.

What's a good alternative to Granite 4.1 8B?

Granite 4.0 Micro (27 t/s) is the closest alternative on this metric. See the full ranking above for the tradeoffs.

How many IBM models are there?

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.

More IBM rankings

All rankings