Aiqre

Model library / ibm-granite

granite-4.2-30b

Granite-4.2-30B is a 29.3 billion-parameter decoder-only language model from IBM, designed for reasoning tasks with built-in chain-of-thought.

29.3B

Parameters in total

131,072

Context length in tokens, as published

55 GiB

Weights at the released precision

apache-2.0

Licence declared on the repository

Overview

What this model is.

Granite-4.2-30B is IBM's flagship model in the Granite 4.2 series. IBM describes it as an open-source, decoder-only transformer aimed at enterprise and research applications that need versatile, safe and efficient language processing. It includes native chain-of-thought reasoning to improve performance on mathematics, coding, multi-step logic and tool-calling tasks.

The model contains 29.3 billion parameters in a dense transformer without expert layers, using bfloat16 weights. It supports a 131,072-token context window, enabling long documents and multi-turn interactions. Distributed under the Apache 2.0 licence, it can be used commercially without restriction. Deployment must accommodate the memory and compute demands of a 30 billion-parameter model.

Specification

The published shape.

Repositoryibm-granite/granite-4.2-30b
Publisheribm-granite
Published7 August 2026
ArchitectureGraniteForCausalLM
Model typegranite
Parameters29,276,770,304
Layers64
Hidden size4,096
Attention heads32, 8 key/value heads
Context length131,072 tokens
Vocabulary100,352 tokens
Weight formatbfloat16
Licenceapache-2.0
Base modelibm-granite/granite-4.1-30b-base

Memory

How much VRAM the weights need.

Parameter count multiplied by the bytes each format uses. The key-value cache comes on top.

PrecisionWeightsNotes
bf1654.5 GiBFull precision as released
fp827.3 GiB8-bit, near-lossless on most models
int413.6 GiB4-bit, smallest footprint

The cache costs 256 KiB per token at 16-bit, so the full 131,072-token context of one request needs about 32.0 GiB. Concurrency multiplies that number, not the weights.

Hardware

Which card runs it.

At the released precision, with 90% of the card given to the server and 2.5 GiB kept for the runtime. The context column is what is left for the cache on that setup.

GPUCards neededFree for cacheContext it holds
RTX 4090 24GB 4 21.9 GiB about 89,570 tokens
RTX 5090 32GB 4 50.7 GiB the full 131,072 tokens
L40S 48GB 2 26.9 GiB about 110,050 tokens
A100 80GB 1 15.0 GiB about 61,307 tokens
H100 80GB 1 15.0 GiB about 61,307 tokens
RTX PRO 6000 96GB 1 29.4 GiB about 120,290 tokens
H200 141GB 1 69.9 GiB the full 131,072 tokens

Serving

Running it yourself.

A vLLM launch line for the shape above. Check the model card for a runtime the publisher recommends.

vllm serve ibm-granite/granite-4.2-30b \
  --max-model-len 86016 \
  --gpu-memory-utilization 0.90

Questions

The things people ask about this model.

How much GPU memory does granite-4.2-30b need?

The weights take about 55 GiB at the released precision. That fits on one A100 80GB, which leaves roughly 15 GiB for the key-value cache.

What licence does granite-4.2-30b use?

The repository declares apache-2.0. Read the licence text before commercial use: the name alone does not tell you what is allowed.

How long a context does it support?

The configuration allows 131,072 tokens. Whether the whole window is usable depends on the memory left for the cache, which the hardware table works out per card.

Can I use it through an API instead of hosting it?

This page is a reference, and Aiqre does not serve this model today. We deploy open-weight models on dedicated EU hardware on request, so if you want an OpenAI-compatible endpoint for it, email [email protected] with the model name and roughly what volume you expect.

Also in the library

Related models.

ibm-granite/granite-4.2-8b

Granite-4.2-8B is an 8.8 billion-parameter decoder-only language model from IBM, designed for reasoning-intensive tasks.

ibm-granite/granite-4.2-3b

Granite-4.2-3B is a 3.7 billion-parameter decoder-only language model with built-in chain-of-thought reasoning, released by IBM u…

Gryphe/Pantheon-Reasoning-26B-A4B-1.1-V2

Pantheon-Reasoning-26B-A4B-1.1-V2 is a 26.5 billion-parameter Gemma-4 mixture-of-experts finetune aimed at role-play scenarios, i…

nex-agi/Nex-N2.5-mini

Nex-N2.5-mini is a 35.1 billion-parameter mixture-of-experts language model released under Apache-2.0.

Hosting

Want this model on a dedicated EU GPU?

Tell us the model and roughly what volume you expect. We reply with a price and an OpenAI-compatible endpoint, with your prompts never stored.