whatmodel.sh / WizardCoder 33B V1.1

WizardCoder 33B V1.1

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

WizardCoder 33B V1.1 is an open-weights language model from WizardLM, released January 2024. Its published size is 33.34B parameters and a 16k-token context window. Licence: msft-research.

Catalogue identity notes

Maker repo WizardLM/WizardCoder-33B-V1.1 @22d03e1: licence tag None. 33,342,991,360 parameters from the Hugging Face safetensors metadata (dense, so active = total). Released 2024-01: month the maker's Hugging Face repo was created (createdAt 2024-01-04). Fine-tune of DeepSeek-Coder 33B base (Jan 2024). The maker card lists its licence as MSFTResearch (link to the WizardMath LICENSE); repo now served under WizardLMTeam/. Ollama tags wizardcoder:33b-v1.1-q4_K_M, wizardcoder:33b-v1.1-q8_0 (sizes as listed on the tags page, observed 2026-09-29).

49.5±0.7#353 of 719 LLMsfrom 5 benchmark results across 3 sources

$ how it compares

The LLMs ranked either side of WizardCoder 33B V1.1, out of 828 with a score, then more from WizardLM.

#modelscorewhereRAMreleased
422WizardLM-2 8x22B Microsoft50±1local~91GB2024-04
423Nova Pro Amazon50±1api $1.40/M2024-12
424WizardCoder 33B V1.1 WizardLM50±1local~22GB2024-01
425Mistral Small Instruct 22B (2409) Mistral AI49±2local~15GB2024-09
426Qwen2-Math 72B Instruct Alibaba49±1local~32GB2024-08
more from WizardLM
511WizardCoder Python 34B V1.0 WizardLM46±1local~23GB2023-08
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▁▁▁▃▆██▇▆▄▃▁ #261 of 458 · 84% of its score · 2 tests

Beats Qwen3-VL 32B Instruct, Solar Open 100B (102B-A12B), GLM-4.7-Flash here, though they rank higher overall. Trails DeepSeek LLM 67B Chat, QwQ-32B-Preview, Phi-3 Medium 128K Instruct here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
HumanEval +279.9% ✎▁·▁▁▃▄▆▅█▃▁▁ beats 83/99easy · avg 79%▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 56%sharp · several runs
HumanEval+73.2% ✎▁·▁▁▁▃▄▄▄█▃▁ beats 82/99easy · avg 74%▇▇▇▇▇▇▇▇▇▇▇ 28%sharp · at its level
other tests1 not in a task · 16% of its score
testresultvs the others in its rundifficultycountswhy
EvoEval (overall)53.3% ✎▂▂▃▄▄█▁▄▅▃▁▃ beats 38/42medium · avg 55%▇▇▇▇▇▇ 16%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 33B V1.1 · needs ~19.9 GB · from huggingface.co/TheBloke
    chat in the terminal
    llama cli -hf TheBloke/WizardCoder-33B-V1.1-GGUF:Q4_K_M
  3. Or start a local server and open the address it prints (http://localhost:9931)
    llama serve -hf TheBloke/WizardCoder-33B-V1.1-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 33B V1.1 · needs ~19.9 GB · from huggingface.co/TheBloke

    open in LM Studio ↗

  3. Or download it in the terminal
    lms get https://huggingface.co/TheBloke/WizardCoder-33B-V1.1-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 33B V1.1 · needs ~20 GB · from ollama.com
    chat in the terminal
    ollama run wizardcoder:33b-v1.1-q4_K_M

MLX (Mac)

  1. Install MLX (Mac) · Apple silicon Macs only, text only.
    with uv
    uv tool install mlx-lm
    or
    pip install mlx-lm
  2. Run WizardCoder 33B V1.1 · needs ~35.4 GB, Mac only · from huggingface.co/GGorman
    chat in the terminal
    mlx_lm.chat --model GGorman/WizardCoder-33B-V1.1-Q8-mlx
  3. Or start an OpenAI-compatible server at http://localhost:8080/v1
    mlx_lm.server --model GGorman/WizardCoder-33B-V1.1-Q8-mlx

Official weights and documentation: huggingface.co/WizardLM ↗

$ how the score was worked out · EvalPlus / EvalPerf published… 61%, Top Leaderboard Ranking = Top… 34%, WizardLM team vendor-reported… 4%

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 runs2▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 61%Apache-2.0
Top Leaderboard Ranking = Top Coding Proficiency, Always? EvoEval: Evolving Coding Benchmarks via LLM — authors' own runs2▇▇▇▇▇▇▇▇▇▇ 34%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)
prior · pull toward the middle▇ 0%
weighted average= 49.5

$ 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