IBM

Granite 4.2 8B

Generally availableOpen weights131K contextReasoning

Summary

Granite 4.2 8B is an open-weight language model from IBM, released on 31 Aug 2026. It accepts text and generates text, with a 131K-token context window and up to 118K output tokens per response.

Granite 4.2 8B is a dense reasoning model from IBM. It is suited for mathematics, code generation, multilingual dialogue, and agentic workflows that need multi-step reasoning. It supports full, low-effort,...

Last verified 18 Nov 2026. Every figure on this page links to its source.

Specifications

DeveloperIBM
Release date31 Aug 2026 [OpenRouter]
StatusGenerally available
WeightsOpen weights [Hugging Face]
Licenseapache-2.0 [Hugging Face]
Parameters8.8B [Hugging Face]
Context window131K (131,072 tokens) [OpenRouter]
Max output118K tokens [OpenRouter]
InputText [OpenRouter]
OutputText [OpenRouter]
Reasoning modeYes [OpenRouter]
Tool callingYes [OpenRouter]
Structured outputYes [OpenRouter]
Hugging Faceibm-granite/granite-4.2-8b [Hugging Face]

Granite 4.2 8B API pricing by provider

USD per million tokens. Sorted by input price.

We do not currently track a paid API listing for this model.

Running Granite 4.2 8B locally

Estimated memory, from the parameter count and the architecture in config.json on Hugging Face. Includes about 0.8 GB of runtime overhead.

QuantizationWeightsTotal, 8K contextTotal, 32K context
Q4_K_M (4-bit)5.3 GB7.5 GB11 GB
Q8_0 (8-bit)9.3 GB11 GB16 GB
FP16 / BF16 (16-bit)18 GB20 GB24 GB

At 4-bit with an 8K conversation, Granite 4.2 8B needs about 7.5 GB, so it fits on a graphics card with 10 GB or more, such as the NVIDIA GeForce RTX 3080 10 GB. Check your own hardware, or see Best GPU for local LLMs on our sister site AIPCs.

Frequently asked questions

What is the context window of Granite 4.2 8B?

Granite 4.2 8B has a context window of 131,072 tokens (131K) and can generate up to 117,964 tokens in a single response, according to OpenRouter.

Is Granite 4.2 8B open source?

Granite 4.2 8B is an open-weight model: its weights are published on Hugging Face as ibm-granite/granite-4.2-8b under the apache-2.0 license. Check the license terms before commercial use.

When was Granite 4.2 8B released?

IBM released Granite 4.2 8B on 31 Aug 2026, according to OpenRouter.

How much VRAM does Granite 4.2 8B need?

About 7.5 GB at 4-bit (Q4_K_M) with an 8K-token conversation, and about 11 GB at 8-bit. The 4-bit model fits on a graphics card with 10 GB or more, such as the NVIDIA GeForce RTX 3080 10 GB. These are estimates from the model's published parameter count and architecture.

Similar models from other labs

Comparable on output type, weights, release date, price and context window. Prices are the lowest listed, USD per million tokens.

ModelLabReleasedContextInput $/1MOutput $/1MWeights
MiniCPM5-2BOpenbmb6 Sept 2026131K––Open
Muse Glimmer 30BMeta10 Aug 2026131K$0.35$1.50Open
LFM2.5-2.6BLiquid11 Aug 2026128K––Open
Apertus v1.5 8BSwiss AI15 Oct 2026131K––Open
LFM2.5-24B-A2BLiquid13 Oct 2026128K$0.05$0.70Open
Aion-3.0Aion Labs7 Jul 2026131K–––

Change history

  • No longer listed on openrouter

Sources