whatmodel.sh / Granite 4.2 8B

Granite 4.2 8B

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

Granite 4.2 8B is an open-weights language model from IBM, released August 2026. Its published size is 8.79B parameters and a 131k-token context window. Licence: apache-2.0.

59.7±1.1#198 of 719 LLMsfrom 19 benchmark results across 2 sources

$ how it compares

The LLMs ranked either side of Granite 4.2 8B, out of 828 with a score, then more from IBM.

#modelscorewhereRAMreleased
237Qwen3 235B-A22B (Apr 2025, hybrid) Alibaba60±1api $1.23/M +local~76GB2025-04
238Claude 3.5 Sonnet (2024-10-22) Anthropic60±1comparison only2024-10
239Granite 4.2 8B IBM60±1api $0.11/M +local~6.6GB2026-08
240Solar Open 100B (102B-A12B) Upstage60±1local~41GB2025-12
241Qwen3-VL 30B-A3B Thinking Alibaba60±1api $0.75/M +local~21GB2025-09
more from IBM
192Granite 4.2 30B IBM63±1api $0.28/M +local~19GB2026-08
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▁▁▃▆█▆▅▅▅▄▃▁ #156 of 300 · 28% of its score · 6 tests

Beats o1 (2024-12-17), o3-mini, DeepSeek R1 0528 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
SWE-bench Verified lab47.7% ✎▁▁▁▁▁▁▂▄█▆▁▁ beats 37/131hard · avg 23%▇▇▇ 6.6%sharp · at its level · small run
SWE-bench Pro (split unspecified) lab19.1% ✎▃·▁▁▁▂▃▃█▇▃▁ beats 11/55very hard · avg 8.1%▇▇▇ 6.4%sharp · small run
Terminal-Bench 2.1 lab20.6% ✎▁·▁·▁▁▄▃▄█▃▇ beats 4/56very hard · avg 11%▇▇ 5.8%at its level · small run
SWE-bench Multilingual lab30.8% ✎▁··▁▃▂▅▇█▃▃▁ beats 6/60hard · avg 20%▇▇ 4.2%at its level · small run
BFCL V4 (December 2025 archive) lab52.4% ✎▁▁▁▂▇▆▆▆█▂▄▂ beats 75/111medium · avg 39%▇ 2.9%at its level · small run
τ³-bench lab58.1% ✎▁▁▂▁·▁▁·▁▃▂█ beats 11/25medium · avg 37%▇ 2.4%blunt · at its level · small run
coding▁▁▁▃▆██▇▆▄▃▁ #190 of 458 · 27% of its score · 5 tests

Beats Gemini 2.5 Flash, Qwen3.5 4B, Qwen3 30B-A3B Instruct 2507 here, though they rank higher overall. Trails QwQ-32B-Preview, DeepSeek-V2.5, OpenThinker 32B here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
LiveCodeBench v6 (window unspecified) lab73.2% ✎▂▃▄▄▅██▅▄▇▃▆ beats 39/65medium · avg 49%▇▇▇ 6.7%at its level · small run
SWE-bench Verified lab47.7% ✎▁▁▁▁▁▁▂▄█▆▁▁ beats 37/131hard · avg 23%▇▇▇ 6.6%sharp · at its level · small run
SWE-bench Pro (split unspecified) lab19.1% ✎▃·▁▁▁▂▃▃█▇▃▁ beats 11/55very hard · avg 8.1%▇▇▇ 6.4%sharp · small run
SWE-bench Multilingual lab30.8% ✎▁··▁▃▂▅▇█▃▃▁ beats 6/60hard · avg 20%▇▇ 4.2%at its level · small run
SciCode (level unspecified) lab36.1% ✎▁····▃▄▄▄█▆▂ beats 17/34hard · avg 19%▇ 3.3%at its level · small run
chat & writing▁▁▁▃▅▄▅█▆▆▇▃ #228 of 393 * · 17% of its score · 2 tests

Trails Flan-T5 XXL, LFM2.5 1.2B Instruct, Gemma 3 4B here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
LMArena (text)1288.1 ✎▁▁▁▂▃▃▃▆▆▇█▃ beats 120/379avg 1268▇▇▇▇ 11%blunt
Arena-Hard v2 aggregate lab65.2% ✎▁▁··▄▃▁▃█▁▁▇ beats 12/22hard · avg 27%▇▇▇ 6.6%sharp · at its level · small run
math▁▂▃▅▆▅▄█▄▁▁▁ #123 of 398 * · 16% of its score · 2 tests

Beats Claude Sonnet 4.6, MiniMax-M3, MiMo-V2.5 (310B-A15B) here, though they rank higher overall. Trails Olmo 3.1 32B Think here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
AIME 2025 lab86.7% ✎▁·▁▁▁▂▅▆█▇▅▁ beats 104/133medium · avg 59%▇▇▇▇ 10%sharp · small run
HMMT February 2025 lab78.3% ✎▁▁▁▃▁▅▅▃██▁▄ beats 13/31medium · avg 57%▇▇ 5.5%small run
other tests8 not in a task · 28% of its score
testresultvs the others in its rundifficultycountswhy
GPQA (subset unspecified) lab64.1% ✎▂▁▂▂▄▃▆▃▅█▄▃ beats 67/104hard · avg 42%▇▇▇▇ 10%sharp · at its level · small run
MMLU-Pro lab74.0% ✎▁▁·▁▁▁▃▂▄▅█▁ beats 99/188medium · avg 55%▇▇ 5.7%at its level · small run
ProfBench lab41.2% ✎█·········██ beats 1/2hard · avg 24%▇ 2.8%at its level · small run
RULER 128k lab71.4% ✎▃··▅▄▇▅█▇·▃▃ beats 16/32medium · avg 58%▇ 2.8%at its level · small run
IFBench prompt-level lab79.3% ✎█▄▄··▄·▄···▄ beats 5/6medium · avg 62%▇ 2.7%at its level · small run
RULER 64k lab81.0% ✎▁▁·▂·▂▃▅█▂▁▁ beats 10/25easy · avg 71%▇ 2.2%small run
MMLU-ProX-Lite lab61.1% ✎█·········██ beats 1/2hard · avg 33%▇ 2.0%at its level · small run
BIRD (text-to-SQL) lab41.1% ✎█··········█ beats 0/1—not counted yet: no other model in the same run to compare it with

$ where to run it

Through an API

api · Weights & Biases · $0.11/M · $0.1 in / $0.15 out per 1M tokens · 131k context · wandb.ai ↗ · price sourceUSD per 1M text tokens, standard uncached input and output. Product: W&B Inference. API model: ibm-granite/granite-4.2-8b. Settings: service tier=standard, batch=no, cache=uncached input. Additional/excluded charges: Tools, cache storage, priority service and other modalities excluded.. Currency: USD.

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 8B · needs ~5.3 GB · from huggingface.co/ibm-granite
    chat in the terminal
    llama cli -hf ibm-granite/granite-4.2-8b-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-4.2-8b-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 8B · needs ~5.3 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-4.2-8b-GGUF@Q4_K_M -y
  4. Then run lms ls to see its name, and lms chat followed by that name

Ollama

  1. Install Ollama

    download it (macOS / Windows) ↗

    Linux
    curl -fsSL https://ollama.com/install.sh | sh
  2. Run Granite 4.2 8B · needs ~5.77 GB · from ollama.com
    chat in the terminal
    ollama run granite4.2:8b

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 8B · needs ~4.9 GB, Mac only · from huggingface.co/ibm-granite
    chat in the terminal
    mlx_lm.chat --model ibm-granite/granite-4.2-8b-q4-mlx
  3. Or start an OpenAI-compatible server at http://localhost:8080/v1
    mlx_lm.server --model ibm-granite/granite-4.2-8b-q4-mlx

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

$ how the score was worked out · ibm-granite/granite-4.2-30b m… 89%, 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▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 89%Apache-2.0
LMArena leaderboard dataset1▇▇▇ 11%CC BY 4.0
prior · pull toward the middle▇ 1%
weighted average= 59.7

not counted (1)

ibm-granite/granite-4.2-30b model cardBIRD (text-to-SQL) [correct]41.1%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