whatmodel.sh / Granite 34B Code Instruct (8K)

Granite 34B Code Instruct (8K)

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

Granite 34B Code Instruct (8K) is an open-weights language model from IBM, released April 2024. Its published size is 33.72B parameters. Licence: apache-2.0.

Catalogue identity notes

Comparison-only. Maker repo ibm-granite/granite-34b-code-instruct-8k @4bdfb58: licence tag apache-2.0. 33,715,603,456 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.

45.8±1.2#429 of 719 LLMsfrom 11 benchmark results across 4 sources

$ how it compares

The LLMs ranked either side of Granite 34B Code Instruct (8K), out of 828 with a score, then more from IBM.

#modelscorewhereRAMreleased
508Yi 1.5 34B Chat 01.AI46±1local~22GB2024-05
509DBRX Instruct Databricks46±1local~85GB2024-03
510Granite 34B Code Instruct (8K) IBM46±1local~22GB2024-04
511WizardCoder Python 34B V1.0 WizardLM46±1local~23GB2023-08
512Gemini 1.0 Pro (001) Google46±2comparison only2023-12
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▁▁▁▃▆██▇▆▄▃▁ #298 of 458 · 66% of its score · 7 tests

Beats Solar Open 100B (102B-A12B), GLM-4.7-Flash, Qwen3-VL 30B-A3B Instruct here, though they rank higher overall. Trails DeepSeek LLM 67B Chat, WizardLM 70B V1.0, Yi 1.5 9B Chat here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
HumanEvalSynthesize (HumanEvalPack, 6-language average) lab54.8% ✎▁·▂▁▂▆▅█▄▄▁▂ beats 32/35medium · avg 64%▇▇▇▇▇▇▇▇▇ 23%at its level
HumanEvalExplain (HumanEvalPack, 6-language average) lab41.9% ✎▄▇█▃▄▇▄▁▇▃·▁ beats 33/35medium · avg 49%▇▇▇▇▇▇▇ 17%at its level
HumanEvalFix (HumanEvalPack, 6-language average) lab50.2% ✎▁·▁▁▄██▄█▁▅▅ beats 32/35medium · avg 56%▇▇▇▇▇▇▇ 17%sharp · at its level
CodeReviewQA: solution identification (hard), invariant accuracy19.3% ✎▃··▁▂▂▃▂█▃▄▂ beats 13/47medium · avg 54%▇ 3.4%sharp · at its level · noisy
CodeReviewQA: change localisation (hard), invariant accuracy20.7% ✎█▂▁▁▂▂▂▃▅▅▅▇ beats 20/47medium · avg 36%▇ 3.2%sharp · noisy
CodeReviewQA: automated code refinement, exact match rate35.4% ✎▁▁▁▁▁▁▂▂▃█▅▄ beats 33/47hard · avg 33%▇ 2.4%at its level
CodeReviewQA: change type recognition, invariant accuracy72.3% ✎▁▁▁······▁▃█ beats 22/47easy · avg 67%▇ 0.1%blunt · at its level · noisy
other tests4 not in a task · 34% of its score
testresultvs the others in its rundifficultycountswhy
BigCodeBench (Instruct)35.8% ✎▃▂·▆▆██▆▅▃▃▃ beats 18/33medium · avg 41%▇▇▇▇▇▇ 15%at its level
BigCodeBench (Complete)43.8% ✎▂▁▁▄▂▅▇█▆▂▂▂ beats 40/58medium · avg 50%▇▇▇▇▇▇ 15%at its level
EuroEval HellaSwag (English), test split, 5-shot generative MC, accuracy34.1% ✎▃·▁▁▃▁▂▅█▇▄▁ beats 18/100medium · avg 68%▇ 2.2%at its level · noisy
EuroEval Life in the UK (English knowledge MC), test split, 5-shot, accuracy51.5% ✎▁▁▁▁▁▁▃▂▄█▄▃ beats 20/146easy · avg 83%▇ 1.7%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 34B Code Instruct (8K) · needs ~21.38 GB · from huggingface.co/ibm-granite
    chat in the terminal
    llama cli -hf ibm-granite/granite-34b-code-instruct-8k-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-34b-code-instruct-8k-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 34B Code Instruct (8K) · needs ~21.38 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-34b-code-instruct-8k-GGUF@Q4_K_M -y
  4. Then run lms ls to see its name, and lms chat followed by that name

Ollama

version

  1. Install Ollama

    download it (macOS / Windows) ↗

    Linux
    curl -fsSL https://ollama.com/install.sh | sh
  2. Run Granite 34B Code Instruct (8K) · needs ~19 GB · from ollama.com
    chat in the terminal
    ollama run granite-code:34b

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

$ how the score was worked out · Granite Code Models: A Family… 57%, BigCodeBench paper (Zhuo et a… 30%, CodeReviewQA: The Code Review… 9% and 1 more

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▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 57%CC BY 4.0
BigCodeBench paper (Zhuo et al., ICLR 2025), arXiv 2406.15877v42▇▇▇▇▇▇▇▇▇ 30%CC BY 4.0
CodeReviewQA: The Code Review Comprehension Assessment for Large Language Models (arXiv:2503.16167v2)4▇▇▇ 9%CC-BY-4.0
EuroEval leaderboards (results collection), English generative leaderboard2▇ 4%MIT
prior · pull toward the middle▇ 1%
weighted average= 45.8

$ 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