whatmodel.sh / Granite 4.1 30B

Granite 4.1 30B

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

Granite 4.1 30B is an open-weights language model from IBM, released April 2026. Its published size is 30B parameters. Licence: apache-2.0.

Catalogue identity notes

Comparison-only, proposed so the granite-4-1-8b card runs count. The pinned granite-4.1-8b card (@1504002) prints one Evaluation Results table with '3B Dense', '8B Dense' and '30B Dense' columns for the Granite 4.1 family. Weights: https://huggingface.co/ibm-granite/granite-4.1-30b (sha 4fae6278f7132abf5e971f9de49ebbad09c54cce, created 2026-04-06, apache-2.0, 28,865,728,512 params in safetensors metadata). Dense, so active = total.

55.9±1.1#248 of 719 LLMsfrom 21 benchmark results across 1 source

$ how it compares

The LLMs ranked either side of Granite 4.1 30B, out of 828 with a score, then more from IBM.

#modelscorewhereRAMreleased
297DeepSeek R1 Distill Qwen 32B DeepSeek56±1api $1.59/M +local~21GB2025-01
298Qwen2.5-VL 72B Instruct Alibaba56±1local~46GB2025-01
299Granite 4.1 30B IBM56±1local~19GB2026-04
300Mistral Small 3.2 24B Mistral56±1api $0.11/M +local~16GB2025-06
301DeepSeek-V2.5 (1210) DeepSeek56±1local~82GB2024-12
more from IBM
192Granite 4.2 30B IBM63±1api $0.28/M +local~19GB2026-08
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

see all LLMs · find the ones that fit your machine

$ what it's good at

agent tasks▁▁▃▆█▆▅▅▅▄▃▁ #149 of 300 * · 1.4% of its score · 1 test

Beats o4-mini, o1 (2024-12-17), o3-mini here, though they rank higher overall. Trails SmolLM3 3B, Jamba 1.5 Mini, Jamba 1.5 Large here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
BFCL v3 lab73.7% ✎▁▁▁▁▁▃▅█▆▅▄▁ beats 163/170medium · avg 61%▇ 1.4%blunt · at its level · small run
coding▁▁▁▃▆██▇▆▄▃▁ #206 of 458 · 30% of its score · 7 tests

Beats Qwen3.5 4B, Qwen3-VL 32B Instruct, Solar Open 100B (102B-A12B) here, though they rank higher overall. Trails QwQ-32B-Preview, Ministral 3 3B Reasoning 2512, DeepSeek-Coder-V2 Instruct (0724) here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
HumanEval lab88.4% ✎▁▁▁▁▁▃▅▅█▃▃▁ beats 184/190easy · avg 80%▇▇▇ 7.7%sharp · small run
HumanEval+ lab85.4% ✎▁·▁▁▂▃▄▄█▅▄▃ beats 119/145easy · avg 76%▇▇▇ 7.0%sharp · small run
BigCodeBench lab38.8% ✎▅····▃·█▃▅█▃ beats 9/12hard · avg 32%▇ 3.6%at its level · small run
MBPP lab85.5% ✎▁▁▁▄▅█▄▅▃▁▃▁ beats 78/81easy · avg 76%▇ 3.5%small run
MultiPL-E lab62.3% ✎▃··▄·▅▅▇▄█▃▄ beats 14/31medium · avg 56%▇ 3.5%at its level · small run
MBPP+ lab73.5% ✎▁··▁▁▃▄█▆▄▁▁ beats 95/120easy · avg 67%▇ 2.9%at its level · small run
CRUXEval-O lab55.8% ✎▂▂██▅▂▃·▁·▁▁ beats 46/51medium · avg 48%▇ 2.0%blunt · at its level · small run
chat & writing▁▁▁▃▅▄▅█▆▆▇▃ #149 of 393 * · 2.3% of its score · 1 test

Beats INTELLECT-3, MiniMax-M2, MiniCPM5 2B here, though they rank higher overall. Trails LFM2.5 1.2B Thinking, LFM2.5 8B-A1B, LFM2.5 2.6B here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
IFEval (aggregation unspecified) lab89.6% ✎▁▁▃▁▂▄▄▆█▃▂▁ beats 113/141easy · avg 82%▇ 2.3%small run
math▄··········█ #2 of 3 · 22% of its score · 5 tests

Trails Granite 4.1 8B here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
GSM8K lab94.2% ✎▂▂▂▅▅▆▅▇█▇▄▃ beats 137/146very easy · avg 88%▇▇▇ 7.1%sharp · maxed out · small run
Minerva MATH lab81.3% ✎▄·▂▂·██▆·▆▄▄ beats 21/21easy · avg 68%▇▇ 5.2%small run
DeepMind Mathematics lab81.9% ✎▅····▅·█▃▃·▅ beats 10/10easy · avg 67%▇▇ 5.2%small run
GSM-Symbolic lab75.7% ✎▃▃····▃·▅▅█▃ beats 4/10easy · avg 78%▇ 2.6%small run
MGSM, 5 languages (en, es, fr, ja, zh) lab71.1% ✎█·▄▄██···█·▄ beats 9/10medium · avg 63%▇ 2.2%at its level · small run
other tests7 not in a task · 43% of its score
testresultvs the others in its rundifficultycountswhy
GPQA (subset unspecified) lab45.8% ✎▂▁▂▂▄▃▆▃▅█▄▃ beats 49/104hard · avg 37%▇▇▇▇ 9.3%sharp · at its level · small run
BIG-Bench Hard lab83.7% ✎▁▁▁▁▂▄▅▅█▃▄▁ beats 116/129easy · avg 74%▇▇▇ 8.0%sharp · small run
MMLU lab80.2% ✎▁▁▁▁▁▂▃▅█▃▆▃ beats 136/183medium · avg 70%▇▇ 6.0%at its level · small run
SimpleQA lab6.8% ✎▄▄▄▆█▆███·▂█ beats 8/32very hard · avg 4.8%▇▇ 5.9%too hard for it · small run
MMLU-Pro lab64.1% ✎▁▁·▁▁▁▃▂▄▅█▁ beats 71/188medium · avg 52%▇▇ 5.2%at its level · small run
INCLUDE lab67.3% ✎▂····▂▂▄▄▄█▄ beats 16/36medium · avg 55%▇▇ 4.9%at its level · small run
MMMLU lab73.7% ✎▂▁▁▂▃▂▄▄▅██▃ beats 22/46medium · avg 61%▇▇ 4.1%at its level · small run

$ where to run it

Ollama · recommended

  1. Install Ollama

    download it (macOS / Windows) ↗

    Linux
    curl -fsSL https://ollama.com/install.sh | sh
  2. Run Granite 4.1 30B · needs ~17 GB · from ollama.com
    chat in the terminal
    ollama run granite4.1:30b
$ how the score was worked out · ibm-granite/granite-4.1-8b mo… 99%

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-4.1-8b model card · lab-reported21▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 99%Apache-2.0
prior · pull toward the middle▇ 1%
weighted average= 55.9

$ 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