whatmodel.sh / Qwen2.5 Coder 7B Instruct

Qwen2.5 Coder 7B Instruct

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

Qwen2.5 Coder 7B Instruct is an open-weights language model from Alibaba, released September 2024. Its published size is 7.62B parameters and a 131k-token context window. Licence: apache-2.0.

51.6±1.1#318 of 719 LLMsfrom 15 benchmark results across 5 sources

$ how it compares

The LLMs ranked either side of Qwen2.5 Coder 7B Instruct, out of 828 with a score, then more from Alibaba.

#modelscorewhereRAMreleased
384Aya Expanse 32B Cohere52±2api $0.75/M +local~22GB2024-10
385Gemma 3 12B Google52±1api $0.075/M +local~9.1GB2025-03
386Qwen2.5 Coder 7B Instruct Alibaba52±1local~6GB2024-09
387Qwen2.5 14B Instruct Alibaba52±1local~10GB2024-09
388Cogito v1 Preview Llama 8B Deep Cogito51±5local~6.2GB2025-03
more from Alibaba
18Qwen3.8 Max (2.4T-A95B) Alibaba78±1api $3.00/M +local~380GB2026-08
34Qwen3.8 Max (0902) Alibaba76±1api $3.00/M2026-09
37Qwen3.8-Flash-Next Alibaba75±1local~59GB2026-08

see all LLMs · find the ones that fit your machine

$ what it's good at

coding▁▁▁▃▆██▇▆▄▃▁ #246 of 458 · 94% of its score · 13 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
LiveCodeBench official (Jan 1–Nov 1, 2024)26.2% ✎▁▁·▁▂▄▆█▅▂·▂ beats 13/31hard · avg 26%▇▇▇▇▇▇▇▇▇ 23%sharp · at its level
Aider code editing (133 Exercism Python exercises, two attempts)57.9% ✎▁·▁▂▄▁▆▄█▆▂▂ beats 26/62medium · avg 54%▇▇▇▇▇▇▇▇ 19%at its level
HumanEval lab88.4% ✎▄·▄···█··█·▄ beats 4/6very easy · avg 86%▇▇▇▇▇ 12%sharp
HumanEval+ lab84.1% ✎▄·▄····▄▄·▄█ beats 4/6easy · avg 82%▇▇▇▇ 10%sharp
MBPP lab83.5% ✎█···███·██·█ beats 4/6easy · avg 78%▇▇▇ 6.6%typical
MultiPL-E lab76.5% ✎▄·▄····▄▄·▄█ beats 4/6easy · avg 71%▇▇ 5.8%at its level
MBPP+ lab71.7% ✎▄····▄▄·▄·█▄ beats 4/6easy · avg 67%▇▇ 5.2%at its level
CodeReviewQA: change localisation (hard), invariant accuracy10.7% ✎█▂▁▁▂▂▃▃▅▅▅▇ beats 17/47medium · avg 36%▇ 3.4%sharp · at its level · noisy
5 more tests
testresultvs the others in its rundifficultycountswhy
CRUXEval-I lab65.8% ✎█·██·█··█·██ beats 4/6medium · avg 57%▇ 2.8%at its level
CodeReviewQA: solution identification (hard), invariant accuracy55.2% ✎▃··▁▂▂▃▂█▃▄▂ beats 30/47medium · avg 54%▇ 2.7%sharp · at its level · noisy
CodeReviewQA: automated code refinement, exact match rate41.0% ✎▁▁▁▁▁▁▂▂▃█▅▄ beats 40/47hard · avg 33%▇ 2.2%at its level
CRUXEval-O lab65.9% ✎▄·█··▄·▄··▄▄ beats 4/6medium · avg 55%▇ 1.0%blunt · at its level
CodeReviewQA: change type recognition, invariant accuracy78.6% ✎▁▁▁······▁▃█ beats 43/47easy · avg 67%▇ 0.0%blunt · at its level · noisy
other tests2 not in a task · 5.7% of its score
testresultvs the others in its rundifficultycountswhy
BigCodeBench (Instruct) lab41.0% ✎▄······▄▄█·█ beats 4/6medium · avg 38%▇ 3.6%at its level
Open PT-LLM Leaderboard average (9 Portuguese tasks)71.7% ✎▃▁▁▁▁▁▁▁▂█▅▁ beats 187/276medium · avg 73%▇ 2.1%at its level · 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 Qwen2.5 Coder 7B Instruct · needs ~4.7 GB · from huggingface.co/lmstudio-community
    chat in the terminal
    llama cli -hf lmstudio-community/Qwen2.5-Coder-7B-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/Qwen2.5-Coder-7B-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 Qwen2.5 Coder 7B 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/Qwen2.5-Coder-7B-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 Qwen2.5 Coder 7B Instruct · needs ~5.07 GB · from ollama.com
    chat in the terminal
    ollama run qwen2.5-coder:7b

MLX (Mac)

version

  1. Install MLX (Mac) · Apple silicon Macs only, text only.
    with uv
    uv tool install mlx-lm
    or
    pip install mlx-lm
  2. Run Qwen2.5 Coder 7B Instruct · needs ~4.3 GB, Mac only · from huggingface.co/lmstudio-community
    chat in the terminal
    mlx_lm.chat --model lmstudio-community/Qwen2.5-Coder-7B-Instruct-MLX-4bit
  3. Or start an OpenAI-compatible server at http://localhost:8080/v1
    mlx_lm.server --model lmstudio-community/Qwen2.5-Coder-7B-Instruct-MLX-4bit

Official weights and documentation: huggingface.co/Qwen ↗

$ how the score was worked out · Qwen (Alibaba) vendor-reporte… 47%, LiveCodeBench official websit… 23%, Aider code editing benchmark… 19% and 2 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
Qwen (Alibaba) vendor-reported benchmark scores for its own models (qwen.ai launch posts, Qwen2.5-VL and Qwen3-VL technical reports, Qwen3.8-Flash-Next card) · lab-reported8▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 47%Factual vendor-reported score (not licensed content)
LiveCodeBench official website results (2024-12-26)1▇▇▇▇▇▇▇ 23%CC-BY-SA-4.0
Aider code editing benchmark runs (old edit leaderboard)1▇▇▇▇▇▇ 19%Apache-2.0
CodeReviewQA: The Code Review Comprehension Assessment for Large Language Models (arXiv:2503.16167v2)4▇▇▇ 8%CC-BY-4.0
Open Portuguese LLM Leaderboard (archived)1▇ 2%Apache-2.0
prior · pull toward the middle▇ 0%
weighted average= 51.6
$ quantization evidence · 6 measurements

How much of the full-precision result a quantized version kept, measured within one study. Rows from the same study share a table and aren't independent.

precisiontestfull → quantizedkept
AQLM 4-bitBigCodeBench (Python) pass@10.41 → 0.41100.0%source ↗
AWQ 4-bitBigCodeBench (Python) pass@10.41 → 0.41100.0%source ↗
bitsandbytes NF4 (double quantization)BigCodeBench (Python) pass@10.41 → 0.3995.1%source ↗
GGUF Q4_K_MBigCodeBench (Python) pass@10.41 → 0.497.6%source ↗
GPTQ 4-bitBigCodeBench (Python) pass@10.41 → 0.41100.0%source ↗
QuIP# 4-bitBigCodeBench (Python) pass@10.41 → 0.3278.0%source ↗

$ 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