whatmodel.sh / Qwen2.5-VL 7B Instruct

Qwen2.5-VL 7B Instruct

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

Qwen2.5-VL 7B Instruct is an open-weights language model from Alibaba, released January 2025. Its published size is 8.29B parameters. Licence: apache-2.0.

Catalogue identity notes

Qwen's Qwen2.5-VL 7B Instruct (Qwen/Qwen2.5-VL-7B-Instruct @cc59489, created 2025-01-26, licence apache-2.0). The Qwen2.5-VL technical report (arXiv 2502.13923v1) evaluates the released Instruct models; its 'Qwen2.5-VL 7B' columns are this checkpoint. ollama qwen2.5vl:7b tags package the same model. Smaller siblings of the catalogued qwen2-5-vl-32b / qwen2-5-vl-72b.

Model information sources

Release date ↗ · Weights licence ↗

HF safetensors metadata (dense).

49.8±1.0#347 of 719 LLMsfrom 14 benchmark results across 2 sources

$ how it compares

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

#modelscorewhereRAMreleased
415Gemma 2 27B IT Google50±1local~18GB2024-06
416Bielik 11B v2.3 Instruct SpeakLeash50±2local~8.6GB2024-08
417Qwen2.5-VL 7B Instruct Alibaba50±1local~6.4GB2025-01
418Molmo 72B (0924) Ai250±2local~309GB2024-09
419Codestral 22B v0.1 Mistral AI50±1local~15GB2024-05
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

math▁▂▃▅▆▅▄█▄▁▁▁ #242 of 398 * · 12% of its score · 1 test

Beats Command A (03-2025), GPT-4o (2024-11-20), GPT-4 Turbo (2024-04-09) here, though they rank higher overall. Trails DeepSeek R1 Distill Qwen 1.5B, Tulu 2 DPO 70B, OpenThinker 7B here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
MathVista (testmini) lab68.2% ✎▃··▃▅·▃█▅▅▅█ beats 4/16medium · avg 69%▇▇▇▇▇ 12%at its level
vision & documents▁▁▃▂▃▃▄▂▆▇█▄ #119 of 147 · 100% of its score · 14 tests

Beats DeepSeek V4 Flash Vision (Exp), Gemma 3 12B, Llama 3.2 90B Vision Instruct here, though they rank higher overall. Trails Qwen3.5 2B here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
CharXiv (reasoning questions) lab42.5% ✎▄▂▄▆▄▄▆··▄█▂ beats 4/21medium · avg 39%▇▇▇▇▇▇▇ 17%at its level
CharXiv descriptive questions lab73.9% ✎▄··▂▃▂·▂▄▄▂█ beats 3/14easy · avg 74%▇▇▇▇▇▇ 16%at its level
MMMU (val) lab58.6% ✎▂···▆▃▂▂▄▄▄█ beats 4/16medium · avg 61%▇▇▇▇▇▇ 16%at its level
MathVista (testmini) lab68.2% ✎▃··▃▅·▃█▅▅▅█ beats 4/16medium · avg 69%▇▇▇▇▇ 12%at its level
MMStar lab63.9% ✎▂··▄▂▃·▄█▂▄▆ beats 4/16medium · avg 65%▇▇▇▇ 10%at its level
MMMU Pro lab38.3% ✎▃·█·▅▃▃▃▅▅▃█ beats 3/16medium · avg 46%▇▇▇ 7.9%at its level
ChartArena chart parsing (English, mAP_high average)23.3% ✎▁·▁·▃▃▁▇▃█·▄ beats 3/22hard · avg 27%▇▇ 4.1%blunt · at its level
HallusionBench lab52.9% ✎▃·▃·▅▃▅▅▃▅█▅ beats 4/16medium · avg 55%▇▇ 4.1%blunt · at its level
6 more tests
testresultvs the others in its rundifficultycountswhy
ChartQA lab87.3% ✎▂··▂·▂▃·▅▂▆█ beats 7/17easy · avg 85%▇ 3.4%blunt
DocVQA lab95.7% ✎▃··▅▃▅▃█▃█▅▅ beats 10/17very easy · avg 94%▇ 3.2%blunt · maxed out
RealWorldQA lab68.5% ✎▅▃·▃▅▅·█·▃▅█ beats 3/16easy · avg 70%▇ 3.0%blunt · at its level
CC-OCR lab77.8% ✎▃··▃▅·▅▅·█▅▃ beats 7/13easy · avg 74%▇ 2.0%blunt · at its level
OCRBench lab86.4% ✎▅█·▃▃█▃▅▅▃·▃ beats 8/16easy · avg 84%▇ 1.1%blunt
TextVQA lab84.9% ✎█······▄·▄▄▄ beats 4/5easy · avg 80%▇ 0.6%blunt

$ 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-VL 7B Instruct · needs ~4.7 GB · from huggingface.co/ggml-org
    chat in the terminal
    llama cli -hf ggml-org/Qwen2.5-VL-7B-Instruct-GGUF:Q4_K_M
  3. Or start a local server and open the address it prints (http://localhost:9931)
    llama serve -hf ggml-org/Qwen2.5-VL-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-VL 7B Instruct · needs ~4.7 GB · from huggingface.co/ggml-org

    open in LM Studio ↗

  3. Or download it in the terminal
    lms get https://huggingface.co/ggml-org/Qwen2.5-VL-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-VL 7B Instruct · needs ~6 GB · from ollama.com
    chat in the terminal
    ollama run qwen2.5vl:7b-q4_K_M

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-VL 7B Instruct · needs ~5.6 GB, Mac only · from huggingface.co/mlx-community
    chat in the terminal
    mlx_lm.chat --model mlx-community/Qwen2.5-VL-7B-Instruct-4bit
  3. Or start an OpenAI-compatible server at http://localhost:8080/v1
    mlx_lm.server --model mlx-community/Qwen2.5-VL-7B-Instruct-4bit

Official weights and documentation: huggingface.co/Qwen ↗

$ how the score was worked out · Qwen (Alibaba) vendor-reporte… 95%, ChartArena: Benchmarking Char… 4%

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-reported13▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 95%Factual vendor-reported score (not licensed content)
ChartArena: Benchmarking Chart Parsing across Languages, Scenarios, and Formats (arXiv:2606.01348v3)1▇ 4%CC BY 4.0
prior · pull toward the middle▇ 0%
weighted average= 49.8

$ 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