Model library / ibm-granite
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.
Parameters in total
Context length in tokens, as published
Weights at the released precision
Licence declared on the repository
Overview
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
| Repository | ibm-granite/granite-4.2-30b |
| Publisher | ibm-granite |
| Published | 7 August 2026 |
| Architecture | GraniteForCausalLM |
| Model type | granite |
| Parameters | 29,276,770,304 |
| Layers | 64 |
| Hidden size | 4,096 |
| Attention heads | 32, 8 key/value heads |
| Context length | 131,072 tokens |
| Vocabulary | 100,352 tokens |
| Weight format | bfloat16 |
| Licence | apache-2.0 |
| Base model | ibm-granite/granite-4.1-30b-base |
Memory
Parameter count multiplied by the bytes each format uses. The key-value cache comes on top.
| Precision | Weights | Notes |
|---|---|---|
| bf16 | 54.5 GiB | Full precision as released |
| fp8 | 27.3 GiB | 8-bit, near-lossless on most models |
| int4 | 13.6 GiB | 4-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
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.
| GPU | Cards needed | Free for cache | Context 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
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 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.
The repository declares apache-2.0. Read the licence text before commercial use: the name alone does not tell you what is allowed.
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.
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
Granite-4.2-8B is an 8.8 billion-parameter decoder-only language model from IBM, designed for reasoning-intensive tasks.
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…
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-N2.5-mini is a 35.1 billion-parameter mixture-of-experts language model released under Apache-2.0.
Hosting
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.