whatmodel.sh / WizardCoder Python 34B V1.0

WizardCoder Python 34B V1.0

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

WizardCoder Python 34B V1.0 is an open-weights language model from WizardLM, released August 2023. Its published size is 34B parameters and a 16k-token context window. Licence: llama2.

Catalogue identity notes

Maker repo WizardLM/WizardCoder-Python-34B-V1.0 @897fc6d: licence tag llama2. Parameters: nominal size from the model name (no safetensors metadata in the repo) (dense, so active = total). Released 2023-08: month the maker's Hugging Face repo was created (createdAt 2023-08-26). Evol-Instruct fine-tune of Code Llama 34B Python. Ollama tags wizardcoder:34b-python-q4_K_M, wizardcoder:34b-python-q8_0 (sizes as listed on the tags page, observed 2026-09-29).

45.8±0.7#430 of 719 LLMsfrom 8 benchmark results across 4 sources

$ how it compares

The LLMs ranked either side of WizardCoder Python 34B V1.0, out of 828 with a score, then more from WizardLM.

#modelscorewhereRAMreleased
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
513Mistral Medium (2312) Mistral46±1comparison only2023-12
more from WizardLM
424WizardCoder 33B V1.1 WizardLM50±1local~22GB2024-01
592WizardCoder Python 13B V1.0 WizardLM42±2local~9.8GB2023-08
600WizardCoder-15B-V1.0 WizardLM42±1local~12GB2023-06

see all LLMs · find the ones that fit your machine

$ what it's good at

coding▁▁▁▃▆██▇▆▄▃▁ #308 of 458 · 88% of its score · 5 tests

Beats Solar Open 100B (102B-A12B), GLM-4.7-Flash, Qwen3 4B Instruct 2507 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
HumanEval +273.2% ✎▁·▁▁▃▄▆▅█▃▁▁ beats 66/99easy · avg 79%▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 54%sharp · at its level · several runs
HumanEval+64.6% ✎▁·▁▁▁▃▄▄▄█▃▁ beats 59/99easy · avg 74%▇▇▇▇▇▇▇▇▇▇ 26%sharp · at its level
MBPP+63.2% ✎▁···▁▁▂▅▇█▆▂ beats 44/75easy · avg 68%▇▇ 4.6%at its level
CRUXEval-I42.7% ✎▁··▁▅▂█▇▁··▁ beats 15/22medium · avg 54%▇ 1.6%at its level
CRUXEval-O43.4% ✎▁·▂▃▁█▁▂···▁ beats 16/22medium · avg 53%▇ 1.5%blunt · at its level
other tests1 not in a task · 12% of its score
testresultvs the others in its rundifficultycountswhy
EvoEval (overall)40.8% ✎▂▂▃▄▄█▁▄▅▃▁▃ beats 27/42medium · avg 55%▇▇▇▇▇ 12%at its level

$ 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 WizardCoder Python 34B V1.0 · needs ~20.2 GB · from huggingface.co/TheBloke
    chat in the terminal
    llama cli -hf TheBloke/WizardCoder-Python-34B-V1.0-GGUF:Q4_K_M
  3. Or start a local server and open the address it prints (http://localhost:9931)
    llama serve -hf TheBloke/WizardCoder-Python-34B-V1.0-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 WizardCoder Python 34B V1.0 · needs ~20.2 GB · from huggingface.co/TheBloke

    open in LM Studio ↗

  3. Or download it in the terminal
    lms get https://huggingface.co/TheBloke/WizardCoder-Python-34B-V1.0-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 WizardCoder Python 34B V1.0 · needs ~20 GB · from ollama.com
    chat in the terminal
    ollama run wizardcoder:34b-python-q4_K_M

Official weights and documentation: huggingface.co/WizardLM ↗

$ how the score was worked out · EvalPlus / EvalPerf published… 63%, Top Leaderboard Ranking = Top… 30%, WizardLM team vendor-reported… 4% 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
EvalPlus / EvalPerf published evaluation runs3▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 63%Apache-2.0
Top Leaderboard Ranking = Top Coding Proficiency, Always? EvoEval: Evolving Coding Benchmarks via LLM — authors' own runs2▇▇▇▇▇▇▇▇▇ 30%CC BY 4.0
WizardLM team vendor-reported scores for its own WizardCoder models (Hugging Face card) · lab-reported1▇ 4%Factual vendor-reported score (not licensed content)
CRUXEval published evaluation results (authors' generations and scores)2▇ 3%MIT
prior · pull toward the middle▇ 0%
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