whatmodel.sh / Granite 3.1 3B-A800M Instruct

Granite 3.1 3B-A800M Instruct

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

Granite 3.1 3B-A800M Instruct is an open-weights language model from IBM, released December 2024. Its published size is 3.3B parameters (0.8B active per token) and a 131k-token context window. Licence: apache-2.0.

Catalogue identity notes

IBM Granite-3.1-3B-A800M-Instruct (ibm-granite/granite-3.1-3b-a800m-instruct @a027806, created 2024-12-06, apache-2.0, 3,298,793,472 params; card: '# Parameters 3.3B', '# Active parameters 800M'). Lab rows from its own card tables with the catalogued Granite 3.1 8B/2B instruct siblings.

Model information sources

Release date ↗ · Weights licence ↗

Card architecture table '# Parameters 3.3B' / '# Active parameters 800M' (HF safetensors metadata 3,298,793,472).

34.5±1.7#607 of 719 LLMsfrom 6 benchmark results across 1 source

$ how it compares

The LLMs ranked either side of Granite 3.1 3B-A800M Instruct, out of 828 with a score, then more from IBM.

#modelscorewhereRAMreleased
700DeepSeek LLM 7B Chat DeepSeek35±2local~5.7GB2023-11
701StarCoder 15.5B BigCode35±1local~11GB2023-04
702Granite 3.1 3B-A800M Instruct IBM35±2local~3.6GB2024-12
703Llama 2 13B (base) Meta34±1local~9.3GB2023-07
704Code Llama 7B (base) Meta34±1local~5.5GB2023-08
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

chat & writing▁▁▁▃▅▄▅█▆▆▇▃ #318 of 393 * · 7.4% of its score · 1 test

Beats Gemma 4 E4B, OpenThinker3 7B, Gemma 4 E2B here, though they rank higher overall. Trails LFM2 350M, Gemma 3 1B, Flan-T5 XXL here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
IFEval (aggregation unspecified) lab55.2% ✎▁▁▃▁▂▄▄▆█▃▂▁ beats 19/141easy · avg 78%▇▇▇ 7.4%at its level
math▁▂▃▅▆▅▄█▄▁▁▁ #359 of 398 * · 28% of its score · 1 test

Beats Yi 34B Chat, Llama 3 8B Instruct, Command R (03-2024) here, though they rank higher overall. Trails Gemma 3 1B, Stable Code 3B, Qwen3 0.6B here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
GSM8K lab49.0% ✎▂▂▂▅▅▆▅▇█▇▄▃ beats 45/146very easy · avg 85%▇▇▇▇▇▇▇▇▇▇▇ 28%sharp · at its level
other tests4 not in a task · 64% of its score
testresultvs the others in its rundifficultycountswhy
ARC Challenge lab50.4% ✎▆▁▁▂▂▅▇█▄▃▃▂ beats 58/97easy · avg 82%▇▇▇▇▇▇▇▇▇▇ 26%sharp · at its level
WinoGrande lab64.9% ✎▁···▂▁▁▅█▇▃▁ beats 39/87easy · avg 84%▇▇▇▇▇▇▇ 17%at its level
HellaSwag lab73.0% ✎▁▁▁▁▂▂▃▇█▆▅▃ beats 48/85very easy · avg 89%▇▇▇▇▇ 13%at its level
MMLU lab52.2% ✎▁▁▁▁▁▂▃▅█▃▆▃ beats 42/183easy · avg 75%▇▇▇ 8.2%at its level

$ where to run it

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 3.1 3B-A800M Instruct · needs ~2 GB · from huggingface.co/lmstudio-community
    chat in the terminal
    llama cli -hf lmstudio-community/granite-3.1-3b-a800m-instruct-GGUF:Q4_K_M
  3. Or start a local server and open the address it prints (http://localhost:9931)
    llama serve -hf lmstudio-community/granite-3.1-3b-a800m-instruct-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 3.1 3B-A800M Instruct · needs ~2 GB · from huggingface.co/lmstudio-community

    open in LM Studio ↗

  3. Or download it in the terminal
    lms get https://huggingface.co/lmstudio-community/granite-3.1-3b-a800m-instruct-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 3.1 3B-A800M Instruct · needs ~2 GB · from ollama.com
    chat in the terminal
    ollama run granite3.1-moe:3b

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

$ how the score was worked out · ibm-granite/granite-3.1-3b-a8… 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-3.1-3b-a800m-instruct model card · lab-reported6▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 99%Apache-2.0
prior · pull toward the middle▇ 1%
weighted average= 34.5

$ 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