whatmodel.sh / Qwen2-Math 72B Instruct

Qwen2-Math 72B Instruct

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

Qwen2-Math 72B Instruct is an open-weights language model from Alibaba, released August 2024. Its published size is 72.71B parameters and a 4k-token context window. Licence: tongyi-qianwen.

Catalogue identity notes

Qwen/Qwen2-Math-72B-Instruct @5c26788 (created 2024-08-08, licence tongyi-qianwen). Math-specialised Qwen2 instruct model (English). Lab rows from the Qwen2.5-Math report Table 3 (rule b; with the catalogued Qwen2-1.5B/7B/72B-Instruct columns); independent LiveBench 2024-07-26 row.

Model information sources

Release date ↗ · Weights licence ↗

HF safetensors metadata 72,706,203,648 parameters (Qwen/Qwen2-Math-72B-Instruct @5c26788).

49.4±1.3#355 of 719 LLMsfrom 4 benchmark results across 2 sources

$ how it compares

The LLMs ranked either side of Qwen2-Math 72B Instruct, out of 828 with a score, then more from Alibaba.

#modelscorewhereRAMreleased
424WizardCoder 33B V1.1 WizardLM50±1local~22GB2024-01
425Mistral Small Instruct 22B (2409) Mistral AI49±2local~15GB2024-09
426Qwen2-Math 72B Instruct Alibaba49±1local~32GB2024-08
427OLMo 2 32B Instruct (0325) Ai249±1local~21GB2025-03
428OpenThinker2 7B Open Thoughts49±2local~6.4GB2025-04
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

math▁▂▃▅▆▅▄█▄▁▁▁ #223 of 398 · 37% of its score · 3 tests

Beats GPT-4o (2024-08-06), Command A (03-2025), GPT-4o (2024-11-20) here, though they rank higher overall. Trails Olmo 3 7B Instruct, DeepSeek R1 Distill Llama 8B, Phi-4-mini-reasoning 3.8B here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
Minerva MATH lab40.1% ✎▃·····▃··█▅▅ beats 7/8medium · avg 37%▇▇▇▇▇▇ 16%at its level
GSM8K lab96.7% ✎▄···█▄▄·▄·▄█ beats 8/8very easy · avg 92%▇▇▇▇▇ 12%sharp
MATH (subset unspecified) lab84.0% ✎▃····▃·▅·▅·█ beats 7/8easy · avg 76%▇▇▇▇ 8.8%at its level
other tests1 not in a task · 62% of its score
testresultvs the others in its rundifficultycountswhy
LiveBench 2024-07-2634.2% ✎▁▁▁▂▂▃▂█▆▃▅▃ beats 35/61medium · avg 41%▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 62%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 Qwen2-Math 72B Instruct · needs ~47.4 GB · from huggingface.co/lmstudio-community
    chat in the terminal
    llama cli -hf lmstudio-community/Qwen2-Math-72B-Instruct-GGUF:Q4_K_M
  3. Or start a local server and open the address it prints (http://localhost:9931)
    llama serve -hf lmstudio-community/Qwen2-Math-72B-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-Math 72B Instruct · needs ~47.4 GB · from huggingface.co/lmstudio-community

    open in LM Studio ↗

  3. Or download it in the terminal
    lms get https://huggingface.co/lmstudio-community/Qwen2-Math-72B-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-Math 72B Instruct · needs ~41 GB · from ollama.com
    chat in the terminal
    ollama run qwen2-math:72b

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-Math 72B Instruct · needs ~40.9 GB, Mac only · from huggingface.co/mlx-community
    chat in the terminal
    mlx_lm.chat --model mlx-community/Qwen2-Math-72B-Instruct-4bit
  3. Or start an OpenAI-compatible server at http://localhost:8080/v1
    mlx_lm.server --model mlx-community/Qwen2-Math-72B-Instruct-4bit

Official weights and documentation: huggingface.co/Qwen ↗

$ how the score was worked out · LiveBench model judgments (HF… 62%, Qwen (Alibaba) vendor-reporte… 37%

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
LiveBench model judgments (HF livebench/model_judgment, 2024-10-22 revision) with the LiveBench question datasets1▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 62%Apache-2.0 (stated in the LiveBench datasheet)
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-reported3▇▇▇▇▇▇▇▇▇▇▇ 37%Factual vendor-reported score (not licensed content)
prior · pull toward the middle▇ 1%
weighted average= 49.4

$ 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