AI Hub
All models
LLM

Granite 4.0 H Small

IBM

Updated May 22, 2026 · Benchmarks via Artificial Analysis, specs & pricing via OpenRouter · Methodology · Report an error

Specifications

Type
LLM
Released
September 22, 2025
Output speed
524 tok/s
Latency (TTFT)
8.71s
API pricing
$0.10 in · $0.30 out / 1M tokens

Benchmarks

Reasoning

Coding

Math

Compare Granite 4.0 H Small with

See all Granite 4.0 H Small alternatives →