whatmodel.sh / OpenCodeInterpreter-DS-33B

OpenCodeInterpreter-DS-33B

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

OpenCodeInterpreter-DS-33B is an open-weights language model from M-A-P, released February 2024. Licence: apache-2.0.

Catalogue identity notes

Maker repo m-a-p/OpenCodeInterpreter-DS-33B @c7d9400: licence tag apache-2.0. Released 2024-02: month the maker's Hugging Face repo was created (createdAt 2024-02-19).

50.1±0.9#341 of 719 LLMsfrom 3 benchmark results across 1 source

$ how it compares

The LLMs ranked either side of OpenCodeInterpreter-DS-33B, out of 828 with a score, then more from M-A-P.

#modelscorewhereRAMreleased
409EXAONE Deep 2.4B LG AI Research50±2local~3.2GB2025-03
410Mellum2 12B-A2.5B Instruct JetBrains50±2local~8.6GB2026-05
411OpenCodeInterpreter-DS-33B M-A-P50±1local~22GB2024-02
412Llama 3.2 90B Vision Instruct Meta50±1local~58GB2024-09
413DeepSeek-Coder 33B Instruct DeepSeek50±1local~21GB2023-11
more from M-A-P
431OpenCodeInterpreter-DS-6.7B M-A-P49±1local~5.8GB2024-02

see all LLMs · find the ones that fit your machine

$ what it's good at

coding▁▁▁▃▆██▇▆▄▃▁ #257 of 458 · 100% 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 DeepSeek LLM 67B Chat, QwQ-32B-Preview, Phi-3 Medium 128K Instruct here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
HumanEval79.3% ✎▁·▁▁▃▄▆▅█▃▁▁ beats 82/99easy · avg 79%▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 49%sharp
HumanEval+73.8% ✎▁·▁▁▁▃▄▄▄█▃▁ beats 83/99easy · avg 74%▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 42%sharp · at its level
MBPP+68.5% ✎▁···▁▁▂▅▇█▆▂ beats 57/75easy · avg 68%▇▇▇ 8.5%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 OpenCodeInterpreter-DS-33B · needs ~19.9 GB · from huggingface.co/mradermacher
    chat in the terminal
    llama cli -hf mradermacher/OpenCodeInterpreter-DS-33B-GGUF:Q4_K_M
  3. Or start a local server and open the address it prints (http://localhost:9931)
    llama serve -hf mradermacher/OpenCodeInterpreter-DS-33B-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 OpenCodeInterpreter-DS-33B · needs ~19.9 GB · from huggingface.co/mradermacher

    open in LM Studio ↗

  3. Or download it in the terminal
    lms get https://huggingface.co/mradermacher/OpenCodeInterpreter-DS-33B-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 OpenCodeInterpreter-DS-33B · needs ~19.9 GB · from huggingface.co/mradermacher
    chat in the terminal
    ollama run hf.co/mradermacher/OpenCodeInterpreter-DS-33B-GGUF: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 OpenCodeInterpreter-DS-33B · needs ~19.1 GB, Mac only · from huggingface.co/mlx-community
    chat in the terminal
    mlx_lm.chat --model mlx-community/OpenCodeInterpreter-DS-33B-hf-4bit-mlx
  3. Or start an OpenAI-compatible server at http://localhost:8080/v1
    mlx_lm.server --model mlx-community/OpenCodeInterpreter-DS-33B-hf-4bit-mlx

Other ways to run it

  1. Run it as published · needs ~66.69 GB · from huggingface.co/m-a-p (official)
    uv run --with torch --with 'transformers<5' --with accelerate python -c "from transformers import pipeline; print(pipeline('text-generation', model='m-a-p/OpenCodeInterpreter-DS-33B', torch_dtype='auto', device_map='auto')('Once upon a time', max_new_tokens=40)[0]['generated_text'])"

Official weights and documentation: huggingface.co/m-a-p ↗

$ how the score was worked out · EvalPlus / EvalPerf published… 100%

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▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 100%Apache-2.0
prior · pull toward the middle▇ 0%
weighted average= 50.1

$ 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