whatmodel.sh / Qwen2.5 Coder 0.5B Instruct

Qwen2.5 Coder 0.5B Instruct

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

Qwen2.5 Coder 0.5B Instruct is an open-weights language model from Alibaba, released November 2024. Its published size is 0.49B parameters and a 33k-token context window. Licence: apache-2.0.

Catalogue identity notes

Qwen/Qwen2.5-Coder-0.5B-Instruct @ea3f247 (created 2024-11-06, licence apache-2.0). Smallest Qwen2.5-Coder instruct model. Lab rows from the Qwen2.5-Coder report (rule b) in runs with the catalogued 1.5B/7B/14B/32B and CodeQwen1.5 siblings; independent Aider code-editing row.

Model information sources

Release date ↗ · Weights licence ↗

HF safetensors metadata 494,032,768 parameters (Qwen/Qwen2.5-Coder-0.5B-Instruct @ea3f247).

37.1±1.2#576 of 719 LLMsfrom 9 benchmark results across 2 sources

$ how it compares

The LLMs ranked either side of Qwen2.5 Coder 0.5B Instruct, out of 828 with a score, then more from Alibaba.

#modelscorewhereRAMreleased
667DeepSeek R1 Distill Qwen 1.5B DeepSeek37±2local~2.6GB2025-01
668Gemma 2 2B IT Google37±1local~3.1GB2024-07
669Qwen2.5 Coder 0.5B Instruct Alibaba37±1local~1.8GB2024-11
670Granite 20B Code Base (8K) IBM37±1local~15GB2024-04
671Gemma 1.1 7B IT Google37±1local~7.1GB2024-04
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▁▁▁▃▆██▇▆▄▃▁ #401 of 458 · 96% of its score · 8 tests

Beats DeepSeek R1 Distill Qwen 7B, Qwen3.5 2B, DeepSeek R1 Distill Llama 8B here, though they rank higher overall. Trails Qwen2.5 1.5B Instruct, WizardLM 13B V1.2, Code Llama 7B Instruct here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
HumanEval lab61.6% ✎▄·▄···█··█·▄ beats 0/6very easy · avg 86%▇▇▇▇▇▇▇▇▇▇▇ 28%sharp · at its level
HumanEval+ lab57.3% ✎▄·▄····▄▄·▄█ beats 0/6easy · avg 82%▇▇▇▇▇▇▇▇ 21%sharp · at its level
Aider code editing (133 Exercism Python exercises, two attempts)14.3% ✎▃·▁▂▄▁▆▄█▆▂▂ beats 0/62medium · avg 54%▇▇▇▇▇▇ 16%typical
MBPP lab52.4% ✎█···███·██·█ beats 0/6easy · avg 78%▇▇▇▇▇ 12%at its level
MultiPL-E lab49.6% ✎▄·▄····▄▄·▄█ beats 0/6easy · avg 71%▇▇▇ 8.4%at its level
MBPP+ lab43.7% ✎▄····▄▄·▄·█▄ beats 0/6easy · avg 67%▇▇▇ 7.1%at its level
CRUXEval-I lab33.9% ✎█·██·█··█·██ beats 0/6medium · avg 57%▇ 3.3%at its level
CRUXEval-O lab27.8% ✎▄·█··▄·▄··▄▄ beats 0/6medium · avg 55%▇ 1.2%blunt · at its level
other tests1 not in a task · 3.2% of its score
testresultvs the others in its rundifficultycountswhy
BigCodeBench (Instruct) lab11.1% ✎▄······▄▄█·█ beats 0/6medium · avg 38%▇ 3.2%typical

$ 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 0.5B Instruct · needs ~0.49 GB · from huggingface.co/Qwen (official)
    chat in the terminal
    llama cli -hf Qwen/Qwen2.5-Coder-0.5B-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-0.5B-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 0.5B Instruct · needs ~0.49 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-0.5B-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 0.5B Instruct · needs ~0.398 GB · from ollama.com
    chat in the terminal
    ollama run qwen2.5-coder:0.5b

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 0.5B Instruct · needs ~0.3 GB, Mac only · from huggingface.co/lmstudio-community
    chat in the terminal
    mlx_lm.chat --model lmstudio-community/Qwen2.5-Coder-0.5B-Instruct-MLX-4bit
  3. Or start an OpenAI-compatible server at http://localhost:8080/v1
    mlx_lm.server --model lmstudio-community/Qwen2.5-Coder-0.5B-Instruct-MLX-4bit

Official weights and documentation: huggingface.co/Qwen ↗

$ how the score was worked out · Qwen (Alibaba) vendor-reporte… 83%, Aider code editing benchmark… 16%

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▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 83%Factual vendor-reported score (not licensed content)
Aider code editing benchmark runs (old edit leaderboard)1▇▇▇▇▇ 16%Apache-2.0
prior · pull toward the middle▇ 1%
weighted average= 37.1

$ 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