whatmodel.sh / OpenCoder-8B-Instruct

OpenCoder-8B-Instruct

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

OpenCoder-8B-Instruct is an open-weights language model from INF (infly), released November 2024. Its published size is 7.77B parameters. Licence: other (inf).

Catalogue identity notes

Maker repo infly/OpenCoder-8B-Instruct @01badbb: licence tag other (inf). 7,771,262,976 parameters from the Hugging Face safetensors metadata (dense, so active = total). Released 2024-11: month the maker's Hugging Face repo was created (createdAt 2024-11-07).

51.2±0.9#323 of 719 LLMsfrom 5 benchmark results across 2 sources

$ how it compares

The LLMs ranked either side of OpenCoder-8B-Instruct, out of 828 with a score.

#modelscorewhereRAMreleased
389Hermes 3 Llama 3.1 405B Nous Research51±1local~114GB2024-08
390GPT-4 (0613) OpenAI51±1api $37.50/M2023-06
391OpenCoder-8B-Instruct INF (infly)51±1local~6.4GB2024-11
392Command A Translate (08-2025) Cohere51±5api price unknown2025-08
393Llama 3.1 Nemotron 51B Instruct NVIDIA51±2local~34GB2024-09

see all LLMs · find the ones that fit your machine

$ what it's good at

coding▁▁▁▃▆██▇▆▄▃▁ #242 of 458 · 94% of its score · 3 tests

Beats Qwen3-VL 32B Instruct, Solar Open 100B (102B-A12B), GLM-4.7-Flash here, though they rank higher overall. Trails QwQ-32B-Preview, InternLM2.5 20B Chat, Mistral Small Instruct 22B (2409) here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
HumanEval81.7% ✎▁·▁▁▃▄▆▅█▃▁▁ beats 86/99easy · avg 79%▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 46%sharp
HumanEval+77.4% ✎▁·▁▁▁▃▄▄▄█▃▁ beats 87/99easy · avg 74%▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 40%sharp
MBPP+71.4% ✎▁···▁▁▂▅▇█▆▂ beats 66/75easy · avg 68%▇▇▇ 8.4%at its level
other tests2 not in a task · 5.5% of its score
testresultvs the others in its rundifficultycountswhy
EvalPerf correctness (118 tasks, 20240328)76.9% ✎▂·▂▂▂▆▅▆▆▆▃█ beats 11/29easy · avg 76%▇▇ 4.6%typical
EuroEval Life in the UK (English knowledge MC), test split, 5-shot, accuracy46.2% ✎▁▁▁▁▁▁▃▂▄█▄▃ beats 18/146easy · avg 83%▇ 0.8%noisy

$ 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 OpenCoder-8B-Instruct · needs ~4.7 GB · from huggingface.co/lmstudio-community
    chat in the terminal
    llama cli -hf lmstudio-community/OpenCoder-8B-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/OpenCoder-8B-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 OpenCoder-8B-Instruct · needs ~4.7 GB · from huggingface.co/lmstudio-community

    open in LM Studio ↗

  3. Or download it in the terminal
    lms get https://huggingface.co/lmstudio-community/OpenCoder-8B-Instruct-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 OpenCoder-8B-Instruct · needs ~4.7 GB · from huggingface.co/lmstudio-community
    chat in the terminal
    ollama run hf.co/lmstudio-community/OpenCoder-8B-Instruct-GGUF:Q4_K_M

Other ways to run it

  1. Run it as published · needs ~15.54 GB · from huggingface.co/infly (official)
    uv run --with torch --with 'transformers<5' --with accelerate python -c "from transformers import pipeline; print(pipeline('text-generation', model='infly/OpenCoder-8B-Instruct', torch_dtype='auto', device_map='auto')('Once upon a time', max_new_tokens=40)[0]['generated_text'])"

Official weights and documentation: huggingface.co/infly ↗

$ how the score was worked out · EvalPlus / EvalPerf published… 99%, EuroEval leaderboards (result… 1%

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
EvalPlus / EvalPerf published evaluation runs4▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 99%Apache-2.0
EuroEval leaderboards (results collection), English generative leaderboard1▇ 1%MIT
prior · pull toward the middle▇ 0%
weighted average= 51.2

$ 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