whatmodel.sh / CodeQwen1.5 7B (base)

CodeQwen1.5 7B (base)

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

CodeQwen1.5 7B (base) is an open-weights language model from Alibaba, released April 2024. Its published size is 7.25B parameters and a 66k-token context window. Licence: other (tongyi-qianwen-research).

Catalogue identity notes

Maker repo Qwen/CodeQwen1.5-7B @5ce5a15: licence tag other (tongyi-qianwen-research). 7,250,284,544 parameters from the Hugging Face safetensors metadata (dense, so active = total). Released 2024-04: month the maker's Hugging Face repo was created (createdAt 2024-04-15). Pretrained base checkpoint (not an instruct/chat version).

40.7±0.8#522 of 719 LLMsfrom 4 benchmark results across 2 sources

$ how it compares

The LLMs ranked either side of CodeQwen1.5 7B (base), out of 828 with a score, then more from Alibaba.

#modelscorewhereRAMreleased
612Mixtral 8x7B v0.1 (base) Mistral AI41±1local~29GB2023-12
613North Micro Vision Instruct (2.4B) Cohere41±2local~3.8GB2026-08
614CodeQwen1.5 7B (base) Alibaba41±1local~6.4GB2024-04
615Granite 4.0 1B IBM41±1local~2.4GB2025-10
616Mixtral 8x7B Instruct v0.1 Mistral41±1local~29GB2023-12
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▁▁▁▃▆██▇▆▄▃▁ #370 of 458 · 94% of its score · 3 tests

Beats LFM2.5 8B-A1B, DeepSeek R1 Distill Qwen 7B, Qwen3.5 2B here, though they rank higher overall. Trails Qwen2.5 1.5B Instruct, WizardLM 13B V1.2, Granite 3.0 2B Instruct here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
HumanEval51.8% ✎▁·▁▁▃▄▆▅█▃▁▁ beats 37/99easy · avg 79%▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 51%sharp · at its level
HumanEval+45.7% ✎▁·▁▁▁▃▄▄▄█▃▁ beats 38/99easy · avg 74%▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 37%sharp · at its level
MBPP+60.8% ✎▁···▁▁▂▅▇█▆▂ beats 38/75easy · avg 68%▇▇▇ 6.6%at its level
other tests1 not in a task · 5.9% of its score
testresultvs the others in its rundifficultycountswhy
BigCodeBench (Complete)45.6% ✎▂▁▁▄▂▅▇█▆▂▂▂ beats 43/58medium · avg 50%▇▇ 5.9%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 CodeQwen1.5 7B (base) · needs ~4.7 GB · from huggingface.co/bartowski
    chat in the terminal
    llama cli -hf bartowski/CodeQwen1.5-7B-GGUF:Q4_K_M
  3. Or start a local server and open the address it prints (http://localhost:9931)
    llama serve -hf bartowski/CodeQwen1.5-7B-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 CodeQwen1.5 7B (base) · needs ~4.7 GB · from huggingface.co/bartowski

    open in LM Studio ↗

  3. Or download it in the terminal
    lms get https://huggingface.co/bartowski/CodeQwen1.5-7B-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 CodeQwen1.5 7B (base) · needs ~4.7 GB · from huggingface.co/bartowski
    chat in the terminal
    ollama run hf.co/bartowski/CodeQwen1.5-7B-GGUF:Q4_K_M

Other ways to run it

  1. Run it as published · needs ~14.5 GB · from huggingface.co/Qwen
    uv run --with torch --with 'transformers<5' --with accelerate python -c "from transformers import pipeline; print(pipeline('text-generation', model='Qwen/CodeQwen1.5-7B', torch_dtype='auto', device_map='auto')('Once upon a time', max_new_tokens=40)[0]['generated_text'])"

Weights and documentation: huggingface.co/Qwen ↗

$ how the score was worked out · EvalPlus / EvalPerf published… 94%, BigCodeBench paper (Zhuo et a… 6%

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▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 94%Apache-2.0
BigCodeBench paper (Zhuo et al., ICLR 2025), arXiv 2406.15877v41▇▇ 6%CC BY 4.0
prior · pull toward the middle▇ 0%
weighted average= 40.7

$ 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