Ctrl K
Back to models

IBM

Granite 4.2 30B

  • Released
  • Open weights
  • Apache 2.0
Compare
Intelligence Index

Reasoning setting

12.7#64 of 83measured models
Measured · Artificial Analysis v4.3.2
Context window
131.07K tok

Performance profile

ReasoningRank #81 of 107
64.4%
GPQA Diamond
CodingRank #72 of 94
37.8%
SciCode
Cost efficiencyRank #18 of 67
177.0pts / $
Intelligence ÷ eval cost

Capabilities

Context window

Modalities

Measured setting

Reasoning trade-offs

Source (opens in a new tab)
Intelligence Index v4.3.2
Granite 4.2 30B
Cost per task (USD) · log scale
Granite 4.2 30BReasoning
Intelligence Index
12.7
Cost / task
$0.0717
Evaluation time
10.9m

Pricing & access

No API offering listed in our tracked sources.

Run locally

GGUF
Context
Estimated memory

~20.5 GiB

RAM + VRAM

Estimate assumptions

One text chat at the selected context, with a 16-bit cache and app allowance. Operating system and image processing are extra; optimized caches can use less.

32 GiB RAMwithout GPU offload

Memory budgetOne text chat
Weights
16.5 GiB
Context cache
2 GiB16-bit cache
App allowance
2 GiB
Download
17.7 GB
Disk space
~25 GB
Available software
Ollama (opens in a new tab)LM Studio (opens in a new tab)Jan (opens in a new tab)KoboldCpp (opens in a new tab)llama.cpp (opens in a new tab)
Get GGUF (opens in a new tab)
Set up in Ollama · Q4_K_M · 8K context

Save the following as Modelfile. The context matches the estimate above.

FROM hf.co/lmstudio-community/granite-4.2-30b-GGUF:Q4_K_M
PARAMETER num_ctx 8192

Then run these commands in your terminal:

ollama create llmcurrent-local -f Modelfile
ollama run llmcurrent-local

Ollama import instructions (opens in a new tab) · For LM Studio or Jan, open the app’s model search, enter lmstudio-community/granite-4.2-30b-GGUF, choose Q4_K_M, and set context to 8,192 tokens in the app’s model settings. Software links above open each app’s setup guide.

vLLM setup (opens in a new tab)

Benchmarks

Full leaderboardSource (opens in a new tab)

Humanity’s Last Exam

Frontier reasoning

Granite 4.2 30B · Reasoning#86 of 126

  1. 1Claude Opus 5.5Max61.4%
  2. 2Claude Fable 5.1Max59.1%
  3. 3Gemini 4 ArgonHigh57.1%
  5. 83Command A+Reasoning12.0%
  6. 84Nova 2.0 LiteHigh11.6%
  7. 85NVIDIA Nemotron 3 Nano 30B A3BReasoning11.4%
  8. 86Granite 4.2 30BReasoning11.2%
  9. 87North Mini CodeReasoning11.1%
  10. 88gpt-oss-20bHigh11.0%
  11. 89Hermes 4 - Llama-3.1 405BReasoning10.9%

Peers use their best measured result on this benchmark.

Alternatives

Each model at its highest-scoring measured setting · Intelligence Index v4.3.2 and its evaluation cost per task.