whatmodel.sh / Granite 8B Code Base (4K)

Granite 8B Code Base (4K)

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

Granite 8B Code Base (4K) is an open-weights language model from IBM, released April 2024. Its published size is 8.05B parameters. Licence: apache-2.0.

Catalogue identity notes

Comparison-only. Maker repo ibm-granite/granite-8b-code-base-4k @d21e874: licence tag apache-2.0. 8,054,910,976 parameters from the Hugging Face safetensors metadata (dense, so active = total). Released 2024-04: month the maker's Hugging Face repo was created (createdAt 2024-04-21). May 2024 Granite Code release (repo later suffixed -4k); not the 128K variant.

38.8±1.2#546 of 719 LLMsfrom 10 benchmark results across 3 sources

$ how it compares

The LLMs ranked either side of Granite 8B Code Base (4K), out of 828 with a score, then more from IBM.

#modelscorewhereRAMreleased
636DeepSeek-Coder 6.7B Base DeepSeek39±1local~5.8GB2023-10
637Starling-LM 7B alpha UC Berkeley (NEST)39±1local~6.1GB2023-11
638Granite 8B Code Base (4K) IBM39±1local~6.6GB2024-04
639StarCoder2 15B BigCode39±1local~11GB2024-02
640speechless-code-mistral-7b-v1.0 uukuguy39±1local~17GB2023-10
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

coding▁▁▁▃▆██▇▆▄▃▁ #384 of 458 · 76% of its score · 6 tests

Beats DeepSeek R1 Distill Qwen 7B, Qwen3.5 2B, DeepSeek R1 Distill Llama 8B here, though they rank higher overall. Trails Qwen2.5 1.5B Instruct, WizardLM 13B V1.2, Falcon3 3B Instruct here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
HumanEvalSynthesize (HumanEvalPack, 6-language average) lab43.5% ✎▁·▂▁▂▆▅█▄▄▁▂ beats 24/35medium · avg 64%▇▇▇▇▇▇▇▇▇ 22%at its level
HumanEvalExplain (HumanEvalPack, 6-language average) lab26.4% ✎▄▇█▃▄▇▄▁▇▃·▁ beats 22/35medium · avg 49%▇▇▇▇▇ 13%typical
HumanEvalFix (HumanEvalPack, 6-language average) lab29.6% ✎▁·▁▁▄██▄█▁▅▅ beats 26/35medium · avg 56%▇▇▇▇▇ 12%sharp
MBPP lab42.2% ✎█·▅▃▃▃▅▃▃▅·▅ beats 8/15easy · avg 70%▇▇▇▇▇ 12%at its level
CRUXEval-I lab36.0% ✎▃▅█▃▃▅·▃▃▅·▅ beats 8/15medium · avg 59%▇▇▇▇ 10%at its level
CRUXEval-O lab36.1% ✎▃·▃██▅▃·▃▃▅▃ beats 9/15medium · avg 55%▇▇▇ 7.7%blunt · at its level
math▁▂▃▅▆▅▄█▄▁▁▁ #273 of 398 * · 8.4% of its score · 2 tests

Beats Molmo 2 8B, DeepSeek-Coder-V2 Instruct (0724), Llama 3.1 70B Instruct here, though they rank higher overall. Trails DeepSeek R1 Distill Qwen 1.5B here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
MATH lab21.4% ✎▃·▃····▃···█ beats 3/5medium · avg 40%▇▇ 4.4%noisy
GSM8K lab61.9% ✎▄··▄···▄··█▄ beats 5/5easy · avg 77%▇▇ 4.0%sharp · at its level · noisy
other tests2 not in a task · 15% of its score
testresultvs the others in its rundifficultycountswhy
BigCodeBench (Complete)35.6% ✎▂▁▁▄▂▅▇█▆▂▂▂ beats 17/58medium · avg 50%▇▇▇▇▇ 13%at its level
EuroEval Life in the UK (English knowledge MC), test split, 5-shot, accuracy34.5% ✎▁▁▁▁▃▁▁▂▄█▄▃ beats 9/146easy · avg 83%▇ 1.9%at its level · noisy

$ where to run it

llama.cpp · recommended

  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 8B Code Base (4K) · needs ~4.88 GB · from huggingface.co/ibm-granite
    chat in the terminal
    llama cli -hf ibm-granite/granite-8b-code-base-4k-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-8b-code-base-4k-GGUF:Q4_K_M

LM Studio

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

    download it (macOS / Windows / Linux) ↗

  2. Run Granite 8B Code Base (4K) · needs ~4.88 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-8b-code-base-4k-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 8B Code Base (4K) · needs ~4.88 GB · from huggingface.co/ibm-granite
    chat in the terminal
    ollama run hf.co/ibm-granite/granite-8b-code-base-4k-GGUF:Q4_K_M

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

$ how the score was worked out · Granite Code Models: A Family… 85%, BigCodeBench paper (Zhuo et a… 13%, EuroEval leaderboards (result… 2%

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
Granite Code Models: A Family of Open Foundation Models for Code Intelligence — authors' own runs · lab-reported8▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 85%CC BY 4.0
BigCodeBench paper (Zhuo et al., ICLR 2025), arXiv 2406.15877v41▇▇▇▇ 13%CC BY 4.0
EuroEval leaderboards (results collection), English generative leaderboard1▇ 2%MIT
prior · pull toward the middle▇ 1%
weighted average= 38.8

$ 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