whatmodel.sh / Qwen2.5 Coder 3B Instruct

Qwen2.5 Coder 3B Instruct

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

Qwen2.5 Coder 3B Instruct is an open-weights language model from Alibaba, released November 2024. Its published size is 3.09B parameters and a 33k-token context window. Licence: qwen-research.

Catalogue identity notes

Qwen/Qwen2.5-Coder-3B-Instruct @488639f (created 2024-11-06, licence qwen-research). Qwen2.5-Coder 3B instruct (Qwen Research licence, unlike the Apache-2.0 sizes). Lab rows from the Qwen2.5-Coder report (rule b) with the catalogued siblings; independent Aider code-editing row.

Model information sources

Release date ↗ · Weights licence ↗

HF safetensors metadata 3,085,938,688 parameters (Qwen/Qwen2.5-Coder-3B-Instruct @488639f).

47.6±1.2#388 of 719 LLMsfrom 9 benchmark results across 2 sources

$ how it compares

The LLMs ranked either side of Qwen2.5 Coder 3B Instruct, out of 828 with a score, then more from Alibaba.

#modelscorewhereRAMreleased
463DeepSeek-Coder 7B Instruct v1.5 DeepSeek48±1local~5.9GB2024-01
464Qwen2 57B-A14B Instruct Alibaba48±2local~35GB2024-06
465Qwen2.5 Coder 3B Instruct Alibaba48±1local~3.3GB2024-11
466DeepSeek-Coder 6.7B Instruct DeepSeek48±1local~5.8GB2023-10
467MiniCPM3-4B OpenBMB48±2local~4GB2024-09
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▁▁▁▃▆██▇▆▄▃▁ #302 of 458 · 95% of its score · 8 tests

Beats Solar Open 100B (102B-A12B), GLM-4.7-Flash, Qwen3-VL 30B-A3B Instruct 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
Aider code editing (133 Exercism Python exercises, two attempts)39.1% ✎▁·▁▂▄▁▆▄█▆▂▂ beats 11/62medium · avg 54%▇▇▇▇▇▇▇▇▇▇ 25%at its level
HumanEval lab84.1% ✎▄·▄···█··█·▄ beats 3/6very easy · avg 86%▇▇▇▇▇▇▇▇ 21%sharp
HumanEval+ lab80.5% ✎▄·▄····▄▄·▄█ beats 3/6easy · avg 82%▇▇▇▇▇▇▇ 17%sharp
MBPP lab73.6% ✎█···███·██·█ beats 2/6easy · avg 78%▇▇▇▇ 10%typical
MultiPL-E lab72.1% ✎▄·▄····▄▄·▄█ beats 3/6easy · avg 71%▇▇▇ 8.4%at its level
MBPP+ lab62.4% ✎▄····▄▄·▄·█▄ beats 2/6easy · avg 67%▇▇▇ 7.3%at its level
CRUXEval-I lab53.2% ✎█·██·█··█·██ beats 3/6medium · avg 57%▇▇ 3.8%at its level
CRUXEval-O lab56.0% ✎▄·█··▄·▄··▄▄ beats 3/6medium · avg 55%▇ 1.4%blunt · at its level
other tests1 not in a task · 4.6% of its score
testresultvs the others in its rundifficultycountswhy
BigCodeBench (Instruct) lab35.8% ✎▄······▄▄█·█ beats 2/6medium · avg 38%▇▇ 4.6%at its level

$ where to run it

llama.cpp · recommended

  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 3B Instruct · needs ~2.1 GB · from huggingface.co/Qwen (official)
    chat in the terminal
    llama cli -hf Qwen/Qwen2.5-Coder-3B-Instruct-GGUF:Q4_K_M
  3. Or start a local server and open the address it prints (http://localhost:9931)
    llama serve -hf Qwen/Qwen2.5-Coder-3B-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 3B Instruct · needs ~2.1 GB · from huggingface.co/Qwen (official)

    open in LM Studio ↗

  3. Or download it in the terminal
    lms get https://huggingface.co/Qwen/Qwen2.5-Coder-3B-Instruct-GGUF@Q4_K_M -y
  4. Then run lms ls to see its name, and lms chat followed by that name

Ollama

  1. Install Ollama

    download it (macOS / Windows) ↗

    Linux
    curl -fsSL https://ollama.com/install.sh | sh
  2. Run Qwen2.5 Coder 3B Instruct · needs ~1.9 GB · from ollama.com
    chat in the terminal
    ollama run qwen2.5-coder:3b

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 3B Instruct · needs ~1.7 GB, Mac only · from huggingface.co/lmstudio-community
    chat in the terminal
    mlx_lm.chat --model lmstudio-community/Qwen2.5-Coder-3B-Instruct-MLX-4bit
  3. Or start an OpenAI-compatible server at http://localhost:8080/v1
    mlx_lm.server --model lmstudio-community/Qwen2.5-Coder-3B-Instruct-MLX-4bit

Official weights and documentation: huggingface.co/Qwen ↗

$ how the score was worked out · Qwen (Alibaba) vendor-reporte… 74%, Aider code editing benchmark… 25%

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▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 74%Factual vendor-reported score (not licensed content)
Aider code editing benchmark runs (old edit leaderboard)1▇▇▇▇▇▇▇▇ 25%Apache-2.0
prior · pull toward the middle▇ 1%
weighted average= 47.6

$ 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