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

Granite 8B Code Instruct (4K)

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

Granite 8B Code Instruct (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-instruct-4k @b996987: 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 2024-04-26). May 2024 Granite Code release; not the 128K variant.

43.8±1.4#466 of 719 LLMsfrom 5 benchmark results across 3 sources

$ how it compares

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

#modelscorewhereRAMreleased
553Qwen3-VL 2B Instruct Alibaba44±1local~2.7GB2025-10
554Dolphin 2.6 Mixtral 8x7B Cognitive Computations44±1local~29GB2023-12
555Granite 8B Code Instruct (4K) IBM44±1local~6.6GB2024-04
556Falcon3 10B Instruct TII44±3local~7.6GB2024-12
557Code Tulu 2 34B Allen Institute for AI44±2local~72GB2023-11
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▁▁▁▃▆██▇▆▄▃▁ #328 of 458 · 77% of its score · 3 tests

Beats GLM-4.7-Flash, Qwen3-VL 4B Instruct, LFM2.5 2.6B here, though they rank higher overall. Trails Phi-3-mini-128k-instruct (Apr 2024), DeepSeek LLM 67B Chat, WizardLM 70B V1.0 here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
HumanEvalSynthesize (HumanEvalPack, 6-language average) lab49.6% ✎▁·▂▁▂▆▅█▄▄▁▂ beats 29/35medium · avg 64%▇▇▇▇▇▇▇▇▇▇▇▇▇ 32%at its level
HumanEvalExplain (HumanEvalPack, 6-language average) lab40.9% ✎▄▇█▃▄▇▄▁▇▃·▁ beats 31/35medium · avg 49%▇▇▇▇▇▇▇▇▇ 23%at its level
HumanEvalFix (HumanEvalPack, 6-language average) lab40.4% ✎▁·▁▁▄██▄█▁▅▅ beats 29/35medium · avg 56%▇▇▇▇▇▇▇▇▇ 22%sharp · at its level
other tests2 not in a task · 22% of its score
testresultvs the others in its rundifficultycountswhy
BigCodeBench (Complete)39.2% ✎▂▁▁▄▂▅▇█▆▂▂▂ beats 26/58medium · avg 50%▇▇▇▇▇▇▇▇ 20%at its level
EuroEval Life in the UK (English knowledge MC), test split, 5-shot, accuracy45.2% ✎▁▁▁▁▁▁▃▂▄█▄▃ beats 16/146easy · avg 83%▇ 2.4%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 Instruct (4K) · needs ~4.88 GB · from huggingface.co/ibm-granite
    chat in the terminal
    llama cli -hf ibm-granite/granite-8b-code-instruct-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-instruct-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 Instruct (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-instruct-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 Instruct (4K) · needs ~4.88 GB · from huggingface.co/ibm-granite
    chat in the terminal
    ollama run hf.co/ibm-granite/granite-8b-code-instruct-4k-GGUF:Q4_K_M

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

$ how the score was worked out · Granite Code Models: A Family… 77%, BigCodeBench paper (Zhuo et a… 20%, 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-reported3▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 77%CC BY 4.0
BigCodeBench paper (Zhuo et al., ICLR 2025), arXiv 2406.15877v41▇▇▇▇▇▇ 20%CC BY 4.0
EuroEval leaderboards (results collection), English generative leaderboard1▇ 2%MIT
prior · pull toward the middle▇ 1%
weighted average= 43.8

$ 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