whatmodel.sh / Granite 3.3 2B Instruct

Granite 3.3 2B Instruct

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

Granite 3.3 2B Instruct is an open-weights language model from IBM, released April 2025. Its published size is 2.53B parameters and a 128k-token context window. Licence: apache-2.0.

Catalogue identity notes

Maker repo ibm-granite/granite-3.3-2b-instruct @707f574: licence tag apache-2.0. 2,533,539,840 parameters from the Hugging Face safetensors metadata. Dense, so active = total. Released 2025-04: month the maker's Hugging Face repo was created (createdAt 2025-04-09). Ollama tags granite3.3:2b are the library's instruct/chat builds of this checkpoint (tag names on the pinned tags page); download sizes are estimated from the parameter count. The granite3.3 tags page lists only 2b (1.5GB) and 8b (4.9GB) builds, sizes consistent with 4-bit Q4_K_M; quant inferred from size.

39.4±1.3#540 of 719 LLMsfrom 9 benchmark results across 1 source

$ how it compares

The LLMs ranked either side of Granite 3.3 2B Instruct, out of 828 with a score, then more from IBM.

#modelscorewhereRAMreleased
630Bielik 1.5B v3.0 Instruct SpeakLeash40±3local~2.4GB2025-04
631OpenHermes 2.5 Mistral 7B Nous Research39±1local~6.1GB2023-10
632Granite 3.3 2B Instruct IBM39±1local~3GB2025-04
633Phi-3-mini-128k-instruct (Apr 2024) Microsoft39±2local~9.5GB2024-04
634Mistral 7B Instruct v0.3 Mistral39±1local~5.8GB2024-05
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▁▁▁▃▅▄▅█▆▆▇▃ #314 of 393 * · 12% of its score · 2 tests

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
Arena-Hard (version/judge unspecified) lab28.9% ✎█·▄··▄·····█ beats 2/5medium · avg 58%▇▇▇ 6.3%at its level
IFEval (aggregation unspecified) lab65.8% ✎▄▄·▄······▄█ beats 2/5easy · avg 79%▇▇ 6.1%at its level
math▁▂▃▅▆▅▄█▄▁▁▁ #305 of 398 · 41% of its score · 3 tests

Beats GPT-4 (0613), Athene-70B, Llama 3 70B Instruct here, though they rank higher overall. Trails Gemma 7B (base), DeepSeek R1 Distill Qwen 1.5B, CodeGemma 7B (v1.0) here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
GSM8K lab72.5% ✎█··▄·····▄·█ beats 2/5very easy · avg 90%▇▇▇▇▇▇▇▇ 21%sharp · at its level
AIME 2024 lab3.3% ✎█···▄▄▄····▄ beats 4/5very hard · avg 11%▇▇▇▇ 10%sharp · too hard for it
MATH-500 lab58.1% ✎█···▄·▄▄···▄ beats 4/5easy · avg 74%▇▇▇▇ 9.5%at its level
other tests4 not in a task · 46% of its score
testresultvs the others in its rundifficultycountswhy
BIG-Bench Hard lab63.9% ✎█·▄·····▄▄·▄ beats 2/5easy · avg 84%▇▇▇▇▇▇▇ 17%sharp · at its level
MMLU lab55.9% ✎▄█········▄█ beats 0/5easy · avg 78%▇▇▇▇▇ 13%at its level
DROP lab44.3% ✎▃▃·····▃···█ beats 2/5easy · avg 68%▇▇▇▇ 11%at its level
PopQA lab18.4% ✎▄·█······▄·█ beats 0/5hard · avg 34%▇▇ 4.8%blunt

$ 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 3.3 2B Instruct · needs ~1.5 GB · from huggingface.co/ibm-granite
    chat in the terminal
    llama cli -hf ibm-granite/granite-3.3-2b-instruct-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-3.3-2b-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 3.3 2B Instruct · needs ~1.5 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-3.3-2b-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 3.3 2B Instruct · needs ~2.02 GB · from ollama.com
    chat in the terminal
    ollama run granite3.3:2b

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 3.3 2B Instruct · needs ~1.4 GB, Mac only · from huggingface.co/mlx-community
    chat in the terminal
    mlx_lm.chat --model mlx-community/granite-3.3-2b-instruct-4bit
  3. Or start an OpenAI-compatible server at http://localhost:8080/v1
    mlx_lm.server --model mlx-community/granite-3.3-2b-instruct-4bit

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

$ how the score was worked out · ibm-granite/granite-3.3-8b-in… 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-3.3-8b-instruct model card · lab-reported9▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 99%Apache-2.0
prior · pull toward the middle▇ 1%
weighted average= 39.4

$ 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