whatmodel.sh / DeepSeek-Coder 33B Instruct

DeepSeek-Coder 33B Instruct

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

DeepSeek-Coder 33B Instruct is an open-weights language model from DeepSeek, released November 2023. Its published size is 33.34B parameters and a 16k-token context window. Licence: deepseek.

Catalogue identity notes

Maker repo deepseek-ai/deepseek-coder-33b-instruct @61dc97b: licence tag other (deepseek). 33,342,991,360 parameters from the Hugging Face safetensors metadata (dense, so active = total). Released 2023-11: month the maker's Hugging Face repo was created (createdAt 2023-11-01). DeepSeek-Coder v1 instruct model; not DeepSeek-Coder-V2. Ollama tags deepseek-coder:33b-instruct-q4_K_M, deepseek-coder:33b-instruct-q8_0 (sizes as listed on the tags page, observed 2026-09-29).

49.9±0.6#343 of 719 LLMsfrom 16 benchmark results across 7 sources

$ how it compares

The LLMs ranked either side of DeepSeek-Coder 33B Instruct, out of 828 with a score, then more from DeepSeek.

#modelscorewhereRAMreleased
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
414Yi 34B 200K (base) 01.AI50±5local~23GB2023-11
415Gemma 2 27B IT Google50±1local~18GB2024-06
more from DeepSeek
21DeepSeek V4.1 Flash DeepSeek78±1api $0.26/M +local~537GB2026-09
31DeepSeek V4 Pro (0813) DeepSeek76±1api $1.63/M +local~1010GB2026-08
35DeepSeek V3.2 Speciale DeepSeek76±3comparison only

see all LLMs · find the ones that fit your machine

$ what it's good at

coding▁▁▁▃▆██▇▆▄▃▁ #259 of 458 · 75% of its score · 10 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 +181.1% ✎▁·▁▁▃▄▆▅█▃▁▁ beats 85/99easy · avg 79%▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 37%sharp · several runs
HumanEval+75.0% ✎▁·▁▁▁▃▄▄▄█▃▁ beats 85/99easy · avg 74%▇▇▇▇▇▇▇▇ 20%sharp · at its level
LiveCodeBench official (Jan 1–Nov 1, 2024)21.9% ✎▁▁·▁▂▄▆█▅▂·▂ beats 7/31hard · avg 26%▇▇▇ 7.8%sharp · at its level
MBPP+70.1% ✎▁···▁▁▂▅▇█▆▂ beats 65/75easy · avg 68%▇▇ 4.0%at its level
CRUXEval-I46.5% ✎▁··▁▅▂█▇▁··▁ beats 17/22medium · avg 54%▇ 1.5%at its level
CRUXEval-O49.9% ✎▁·▂▃▁█▁▃···▁ beats 21/22medium · avg 53%▇ 1.4%blunt · at its level
CodeReviewQA: change localisation (hard), invariant accuracy3.2% ✎█▂▁▃▂▂▂▃▅▅▅▇ beats 12/47medium · avg 36%▇ 1.2%sharp · at its level · noisy
CodeReviewQA: solution identification (hard), invariant accuracy9.0% ✎▃··▁▃▂▃▂█▃▄▂ beats 8/47medium · avg 54%▇ 1.0%sharp · at its level · noisy
2 more tests
testresultvs the others in its rundifficultycountswhy
CodeReviewQA: automated code refinement, exact match rate32.8% ✎▁▁▁▁▁▁▂▂▃█▅▄ beats 28/47hard · avg 33%▇ 0.8%at its level
CodeReviewQA: change type recognition, invariant accuracy69.8% ✎▁▁▁······▁▃█ beats 19/47easy · avg 67%▇ 0.0%blunt · at its level · noisy
other tests5 not in a task · 25% of its score
testresultvs the others in its rundifficultycountswhy
EvoEval (overall)56.0% ✎▂▂▃▄▄█▁▄▅▃▃▃ beats 39/42medium · avg 55%▇▇▇▇▇ 11%at its level
BigCodeBench (Instruct)41.8% ✎▃▂·▆▆██▆▅▃▃▃ beats 27/33medium · avg 41%▇▇ 4.7%at its level
BigCodeBench (Complete)51.1% ✎▂▁▁▄▂▅▇█▆▃▂▂ beats 52/58medium · avg 50%▇▇ 4.5%at its level
EvalPerf correctness (118 tasks, 20240328)77.5% ✎▂·▂▂▂▆▅▆▆▆▃█ beats 13/29easy · avg 76%▇ 2.3%typical
DSEffi-Bench Pass (1,000 data-science tasks, greedy)17.5% ✎▅··▃▅·█·▃██▃ beats 1/15hard · avg 24%▇ 1.9%typical

$ 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 DeepSeek-Coder 33B Instruct · needs ~19.9 GB · from huggingface.co/TheBloke
    chat in the terminal
    llama cli -hf TheBloke/deepseek-coder-33B-instruct-GGUF:Q4_K_M
  3. Or start a local server and open the address it prints (http://localhost:9931)
    llama serve -hf TheBloke/deepseek-coder-33B-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 DeepSeek-Coder 33B Instruct · 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/deepseek-coder-33B-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 DeepSeek-Coder 33B Instruct · needs ~20 GB · from ollama.com
    chat in the terminal
    ollama run deepseek-coder:33b-instruct-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 DeepSeek-Coder 33B Instruct · needs ~18.8 GB, Mac only · from huggingface.co/mlx-community
    chat in the terminal
    mlx_lm.chat --model mlx-community/deepseek-coder-33b-instruct
  3. Or start an OpenAI-compatible server at http://localhost:8080/v1
    mlx_lm.server --model mlx-community/deepseek-coder-33b-instruct

Weights and documentation: huggingface.co/deepseek-ai ↗

$ how the score was worked out · EvalPlus / EvalPerf published… 50%, Top Leaderboard Ranking = Top… 25%, BigCodeBench paper (Zhuo et a… 9% and 4 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 runs4▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 50%Apache-2.0
Top Leaderboard Ranking = Top Coding Proficiency, Always? EvoEval: Evolving Coding Benchmarks via LLM — authors' own runs2▇▇▇▇▇▇▇ 25%CC BY 4.0
BigCodeBench paper (Zhuo et al., ICLR 2025), arXiv 2406.15877v42▇▇▇ 9%CC BY 4.0
LiveCodeBench official website results (2024-12-26)1▇▇ 8%CC-BY-SA-4.0
CodeReviewQA: The Code Review Comprehension Assessment for Large Language Models (arXiv:2503.16167v2)4▇ 3%CC-BY-4.0
CRUXEval published evaluation results (authors' generations and scores)2▇ 3%MIT
DSEffi-Bench: Demystifying Large Language Models' Capability in Efficient Data Science Code Generation — authors' own model runs1▇ 2%CC BY 4.0
prior · pull toward the middle▇ 0%
weighted average= 49.9

$ 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