IBM
Granite 4.2 8B InstructOuvert
IBM Granite 4.2 8B lightweight enterprise foundation model with high throughput and low cost.
Intelligence
49.2 #338
AAQI 43.0
Output speed
115 t/s
TTFT 200 ms · ITL 8.7 ms/tok
Blended price (3:1)
$0.22 /1M
In $0.15/M · Out $0.45/M
Context
128K
≈ 320 A4 pages · max out 8192
Quality Domain Radar
6-Axis Frontier Evaluation vs Category Average & Flagship
Granite 4.2 8B Instruct
Claude Mythos Preview (#1)
Average (68)
Radar axes are approximated from category scores where direct benchmark measurements are missing — see Méthodologie.
API deployment
Compare hosts & latency
Throughput, TTFT and cache pricing across Groq, Cerebras, Together, DeepInfra, Fireworks, Bedrock and Azure.
GroqCerebrasTogether AIDeepInfraFireworks AIAWS BedrockAzure AI
Groq
Cerebras
Together AI
DeepInfra
Fireworks AI
AWS Bedrock
Azure AIScores par Source
Scores par Catégorie
Résultats de Benchmarks
Détails du Modèle
Date de Sortie
20 juil. 2026
Paramètres
8 billion
Licence
Open Weights
Fenêtre de Contexte
128,000 tokens
Prix Entrée
$0.15/M
Prix Sortie
$0.45/M
Vitesse Sortie
115 t/s
Temps au Premier Token
200 ms
Estimated monthly bill
Estimated monthly spend
$0.00
Calculating savings vs GPT-4o...
Cite & embed
GitHub Markdown badge
[](https://llmpodium.com/models/granite-4-2-8b)BibTeX
@misc{llmpodium2026granite428b,
title = {Benchmark Analysis and Intelligence Evaluation of Granite 4.2 8B Instruct},
author = {LLMPodium Research},
year = {2026},
url = {https://llmpodium.com/models/granite-4-2-8b}
}More from IBM
Modèles alternatifs
Meilleures alternatives à Granite 4.2 8B Instruct selon les capacités, le prix et les benchmarks.