whatmodel.sh / Granite 4.2 30B

Granite 4.2 30B

+ contribute
Update model informationAdd a place to run itAdd a test resultPropose a benchmarkCorrect a benchmark scoreEdit data on GitHub

Granite 4.2 30B is an open-weights language model from IBM, released August 2026. Its published size is 29.3B parameters and a 131k-token context window. Licence: apache-2.0.

63.0±1.1#166 of 719 LLMsfrom 19 benchmark results across 2 sources

$ how it compares

The LLMs ranked either side of Granite 4.2 30B, out of 828 with a score, then more from IBM.

#modelscorewhereRAMreleased
190Gemini 2.5 Flash Preview (09-2025) Google63±1comparison only2025-09
191Qwen3-Next 80B-A3B Instruct Alibaba63±1api $0.34/M +local~27GB2025-09
192Granite 4.2 30B IBM63±1api $0.28/M +local~19GB2026-08
193o1-preview OpenAI63±1comparison only2024-09
194Gemini 2.5 Flash Preview (04-17) Google63±1comparison only2025-04
more from IBM
239Granite 4.2 8B IBM60±1api $0.11/M +local~6.6GB2026-08
276Granite 4.2 3B IBM57±1api $0.052/M +local~3.7GB2026-08
299Granite 4.1 30B IBM56±1local~19GB2026-04

see all LLMs · find the ones that fit your machine

$ what it's good at

agent tasks▁▁▃▆█▆▅▅▅▄▃▁ #131 of 300 · 31% of its score · 6 tests

Beats o3, Gemini 2.5 Pro, DeepSeek V3.2 Exp here, though they rank higher overall. Trails SmolLM3 3B, Jamba 1.5 Large, GPT-4o (2024-05-13) here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
SWE-bench Pro (split unspecified) lab33.3% ✎▃·▁▁▁▂▂▃█▇▃▁ beats 15/55very hard · avg 8.1%▇▇▇ 7.2%sharp · at its level · small run
SWE-bench Verified lab57.0% ✎▁▁▁▁▁▁▂▄█▆▁▁ beats 47/131hard · avg 23%▇▇▇ 6.9%sharp · at its level · small run
Terminal-Bench 2.1 lab29.2% ✎▁·▁·▁▁▄▃▄█▃▇ beats 8/56very hard · avg 11%▇▇▇ 6.5%at its level · small run
SWE-bench Multilingual lab41.9% ✎▁··▁▃▃▅▇█▃▃▁ beats 8/60hard · avg 20%▇▇ 4.5%at its level · small run
BFCL V4 (December 2025 archive) lab61.4% ✎▁▁▁▂▇▆▆▆█▃▄▂ beats 94/111medium · avg 39%▇ 3.0%at its level · small run
τ³-bench lab62.0% ✎▁▁▂▁·▁▁·▁▁▃█ beats 12/25medium · avg 37%▇ 2.5%blunt · at its level · small run
coding▁▁▁▃▆██▇▆▄▃▁ #146 of 458 · 28% of its score · 5 tests

Beats Gemini 2.5 Pro, Gemini 3.1 Flash-Lite, Qwen3-Coder-Next (80B-A3B) here, though they rank higher overall. Trails Phi-4-reasoning 14B, DeepSeek V3 0324, Devstral Small 2 24B here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
SWE-bench Pro (split unspecified) lab33.3% ✎▃·▁▁▁▂▂▃█▇▃▁ beats 15/55very hard · avg 8.1%▇▇▇ 7.2%sharp · at its level · small run
SWE-bench Verified lab57.0% ✎▁▁▁▁▁▁▂▄█▆▁▁ beats 47/131hard · avg 23%▇▇▇ 6.9%sharp · at its level · small run
LiveCodeBench v6 (window unspecified) lab75.8% ✎▂▃▄▄▅██▅▄▇▃▆ beats 41/65medium · avg 49%▇▇ 6.2%small run
SWE-bench Multilingual lab41.9% ✎▁··▁▃▃▅▇█▃▃▁ beats 8/60hard · avg 20%▇▇ 4.5%at its level · small run
SciCode (level unspecified) lab38.8% ✎▁····▃▄▄▄█▆▂ beats 22/34hard · avg 19%▇ 3.6%at its level · small run
chat & writing▁▁▁▃▅▄▅█▆▆▇▃ #169 of 393 * · 18% of its score · 2 tests

Beats MiniCPM5 2B here, though they rank higher overall. Trails LFM2.5 1.2B Instruct, LFM2.5 1.2B Thinking, Gemma 3 12B here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
LMArena (text)1339.6 ✎▁▁▁▂▃▃▃▆▆▇█▃ beats 177/379avg 1268▇▇▇▇ 11%blunt
Arena-Hard v2 aggregate lab67.9% ✎▁▁··▄▃▁▃█▁▁▇ beats 15/22hard · avg 27%▇▇▇ 6.5%sharp · at its level · small run
math▁▂▃▅▆▅▄█▄▁▁▁ #71 of 398 * · 14% of its score · 2 tests

Beats Claude Sonnet 4.6, Claude Opus 4.5, Qwen3.7 Plus here, though they rank higher overall.

testresultvs the others in its rundifficultycountswhy
AIME 2025 lab89.2% ✎▁·▁▁▁▂▅▆█▇▅▁ beats 112/133medium · avg 59%▇▇▇▇ 8.9%sharp · small run
HMMT February 2025 lab89.2% ✎▁▁▁▃▁▅▅▃██▁▄ beats 17/31medium · avg 57%▇▇ 5.0%small run
other tests8 not in a task · 28% of its score
testresultvs the others in its rundifficultycountswhy
GPQA (subset unspecified) lab66.4% ✎▂▁▂▂▄▃▆▃▅█▄▃ beats 70/104hard · avg 42%▇▇▇▇ 10%sharp · at its level · small run
MMLU-Pro lab77.6% ✎▁▁·▁▁▁▃▂▄▅█▁ beats 112/188medium · avg 55%▇▇ 5.4%small run
ProfBench lab42.9% ✎█·········██ beats 2/2hard · avg 24%▇ 3.0%at its level · small run
RULER 128k lab81.4% ✎▃··▅▄▇▅█▇·▃▃ beats 25/32medium · avg 58%▇ 2.6%small run
IFBench prompt-level lab77.2% ✎█▄▄··▄·▄···▄ beats 4/6medium · avg 62%▇ 2.6%small run
MMLU-ProX-Lite lab66.6% ✎█·········██ beats 2/2hard · avg 33%▇ 2.0%at its level · small run
RULER 64k lab90.0% ✎▁▁·▂·▂▃▅█▂▃▁ beats 24/25easy · avg 71%▇ 2.0%small run
BIRD (text-to-SQL) lab41.9% ✎█··········█ beats 1/1—not counted yet: no other model in the same run to compare it with

$ where to run it

Through an API

api · DeepInfra · $0.28/M · $0.16 in / $0.65 out per 1M tokens · 131k context · deepinfra.com ↗ · price sourceUSD per 1M text tokens. DeepInfra standard synchronous API, model ibm-granite/granite-4.2-30b; uncached input, no batch. Tools, cache storage and other modalities excluded. Provider does not specify quantization. Bertrande, https://bertrande.com/en/ai/deepinfra/ibm-granite--granite-4.2-30b; observed 2026-09-22T10:15:02Z. CC BY 4.0; units normalized and model identifier mapped.

llama.cpp · recommended

version

  1. Install llama.cpp · Homebrew and winget installs name the commands llama-cli and llama-server instead.
    macOS / Linux
    curl -LsSf https://llama.app/install.sh | sh
    Windows
    irm https://llama.app/install.ps1 | iex

    other ways to install ↗

  2. Run Granite 4.2 30B · needs ~17.7 GB · from huggingface.co/ibm-granite
    chat in the terminal
    llama cli -hf ibm-granite/granite-4.2-30b-GGUF:Q4_K_M
  3. Or start a local server and open the address it prints (http://localhost:9931)
    llama serve -hf ibm-granite/granite-4.2-30b-GGUF:Q4_K_M

LM Studio

version

  1. Install LM Studio · Open the app once before using the lms command.

    download it (macOS / Windows / Linux) ↗

  2. Run Granite 4.2 30B · needs ~17.7 GB · from huggingface.co/ibm-granite

    open in LM Studio ↗

  3. Or download it in the terminal
    lms get https://huggingface.co/ibm-granite/granite-4.2-30b-GGUF@Q4_K_M -y
  4. Then run lms ls to see its name, and lms chat followed by that name

Ollama

version

  1. Install Ollama

    download it (macOS / Windows) ↗

    Linux
    curl -fsSL https://ollama.com/install.sh | sh
  2. Run Granite 4.2 30B · needs ~18.08 GB · from ollama.com
    chat in the terminal
    ollama run granite4.2:30b

MLX (Mac)

version

  1. Install MLX (Mac) · Apple silicon Macs only, text only.
    with uv
    uv tool install mlx-lm
    or
    pip install mlx-lm
  2. Run Granite 4.2 30B · needs ~16.5 GB, Mac only · from huggingface.co/ibm-granite
    chat in the terminal
    mlx_lm.chat --model ibm-granite/granite-4.2-30b-q4-mlx
  3. Or start an OpenAI-compatible server at http://localhost:8080/v1
    mlx_lm.server --model ibm-granite/granite-4.2-30b-q4-mlx

Weights and documentation: huggingface.co/ibm-granite ↗

$ how the score was worked out · ibm-granite/granite-4.2-30b m… 88%, LMArena leaderboard dataset 11%

Each result implies a score on its own, after adjusting for how hard its test is and who ran it. The score is their weighted average, with a small pull toward the middle for thinly tested models. Each test's weight is its counts column above; here it's added up by who ran the tests. How it works

sourceresultsshare of the scorelicence
ibm-granite/granite-4.2-30b model card · lab-reported18▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 88%Apache-2.0
LMArena leaderboard dataset1▇▇▇ 11%CC BY 4.0
prior · pull toward the middle▇ 1%
weighted average= 63.0

not counted (1)

ibm-granite/granite-4.2-30b model cardBIRD (text-to-SQL) [correct]41.9%fewer than three models have this test yet, or this source ran it for this model alone

$ improve this page

Update model informationAdd a place to run itAdd a test resultPropose a benchmarkCorrect a benchmark scoreEdit data on GitHub

Use a short GitHub form or edit the data through a pull request. Every number needs a source; here's which ones we can use.

data updated · sources and licences · json