whatmodel.sh / Qwen2-Audio 7B Instruct

Qwen2-Audio 7B Instruct

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

Qwen2-Audio 7B Instruct is an open-weights language model from Alibaba, released July 2024. Its published size is 8.4B parameters. Licence: apache-2.0.

Catalogue identity notes

Comparison-only. Qwen's audio-language chat model, repo Qwen/Qwen2-Audio-7B-Instruct @0a09522 (apache-2.0, created 2024-07-31); AHELM identifier 'qwen2-audio-7b-instruct'. No verified run command recorded.

Model information sources

· Parameter count ↗

8,397,094,912 parameters in the repo's safetensors metadata (AHELM Table 3: 8.4B).

44.2±2.5#454 of 719 LLMsfrom 10 benchmark results across 1 source

$ how it compares

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

#modelscorewhereRAMreleased
541Yi 1.5 9B Chat 01.AI44±1local~6.8GB2024-05
542Command R7B (12-2024) Cohere44±1local~6.2GB2024-12
543Qwen2-Audio 7B Instruct Alibaba44±3local~6.5GB2024-07
544Gemma 3 4B Google44±1api $0.063/M +local~3.8GB2025-03
545Eurus-2-7B-PRIME PRIME-RL44±2local~6.4GB2024-12
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

other tests10 not in a task · 97% of its score
testresultvs the others in its rundifficultycountswhy
AHELM Speech Robust Bench (LibriSpeech-clean with noise) transcription WER39.9% ✎▂·█··▆▄·▂▂·▄ beats 4/13avg 33%▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 51%typical
AHELM CoRe-Bench conversational audio reasoning (pseudo-exact match)23.3% ✎▃·▄··▂▂·▄▂█▄ beats 0/13medium · avg 53%▇▇▇▇▇▇▇ 18%at its level
AHELM LibriSpeech transcription by audio LLMs (WER)11.3% ✎▃···▃·█▃▅▃▅█ beats 2/13avg 11%▇▇▇▇ 11%blunt
AHELM MUStARD audio sarcasm detection (exact match)20.9% ✎▃·······▆█▆▆ beats 0/13very hard · avg 57%▇▇ 5.1%blunt
AHELM AIR-Bench Foundation music subsets (exact match)72.4% ✎▃█▃▅▃·▃·▃▅▃▃ beats 12/13medium · avg 57%▇▇ 4.6%blunt · at its level
AHELM VoxCeleb2 same-speaker detection (exact match)24.0% ✎▃·▂·▂█▂▄▄··▄ beats 0/13very hard · avg 54%▇ 3.6%sharp · too hard for it · noisy
AHELM MELD audio emotion classification (pseudo-exact match)26.0% ✎▃··▃▃▃·▃▅▅█▅ beats 0/13medium · avg 40%▇ 2.6%blunt · at its level
AHELM FLEURS 7-language transcription by audio LLMs (WER)224.0% ✎▄▂···▂▆▂█▂·▂ beats 1/13avg 80%▇ 1.6%blunt · noisy
2 more tests
testresultvs the others in its rundifficultycountswhy
AHELM Multilingual LibriSpeech 7-language transcription by audio LLMs (WER)33.7% ✎▂▂▃··▂▂·▂▂█▆ beats 2/13avg 13%▇ 0.2%blunt · noisy
AHELM VocalSound human-sound recognition (prefix exact match)79.9% ✎██▄▄·█·█·█▄▄ beats 9/13easy · avg 67%▇ 0.1%blunt · 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-Audio 7B Instruct · needs ~4.8 GB · from huggingface.co/mradermacher
    chat in the terminal
    llama cli -hf mradermacher/Qwen2-Audio-7B-Instruct-GGUF:Q4_K_M
  3. Or start a local server and open the address it prints (http://localhost:9931)
    llama serve -hf mradermacher/Qwen2-Audio-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-Audio 7B Instruct · needs ~4.8 GB · from huggingface.co/mradermacher

    open in LM Studio ↗

  3. Or download it in the terminal
    lms get https://huggingface.co/mradermacher/Qwen2-Audio-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-Audio 7B Instruct · needs ~4.8 GB · from huggingface.co/mradermacher
    chat in the terminal
    ollama run hf.co/mradermacher/Qwen2-Audio-7B-Instruct-GGUF:Q4_K_M

Official weights and documentation: huggingface.co/Qwen ↗

$ how the score was worked out · AHELM: A Holistic Evaluation… 97%

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
AHELM: A Holistic Evaluation of Audio-Language Models (Stanford CRFM, arXiv:2508.21376v2)10▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 97%CC BY 4.0
prior · pull toward the middle▇ 3%
weighted average= 44.2

$ 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