whatmodel.sh / Qwen1.5 32B Chat

Qwen1.5 32B Chat

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

Qwen1.5 32B Chat is an open-weights language model from Alibaba, released April 2024. Its published size is 32.51B parameters and a 32k-token context window. Licence: tongyi-qianwen.

Catalogue identity notes

Comparison model from the Epoch AI internal-evaluation CSVs (Epoch release date 2024-04-03). Chat checkpoint Qwen1.5-32B-Chat. 32,512,218,112 parameters. ollama qwen:32b-chat = 32b-chat-v1.5-q4_0 (same digest).

44.0±1.4#459 of 719 LLMsfrom 7 benchmark results across 6 sources

$ how it compares

The LLMs ranked either side of Qwen1.5 32B Chat, out of 828 with a score, then more from Alibaba.

#modelscorewhereRAMreleased
546Llama 3.1 Tulu 3 8B Ai244±1local~6.2GB2024-11
547Qwen2.5-VL 3B Instruct Alibaba44±1local~3.5GB2025-01
548Qwen1.5 32B Chat Alibaba44±1local~22GB2024-04
549Granite 20B Code Instruct (8K) IBM44±1local~14GB2024-04
550Qwen2 7B Instruct Alibaba44±1local~6GB2024-06
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

chat & writing▁▁▁▃▅▄▅█▆▆▇▃ #303 of 393 * · 34% of its score · 2 tests

Beats Gemma 4 E4B, OpenThinker3 7B, Gemma 4 E2B here, though they rank higher overall. Trails LFM2 350M, Gemma 3 1B, Flan-T5 XXL here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
Polyrating rating (bias-aware re-fit of Chatbot Arena votes, mid-2024)1126.0 ✎▂▁▂▁▃▇█▆▇▄▂▂ beats 60/95avg 1201▇▇▇▇▇▇▇ 17%blunt
LMArena (text)1203.9 ✎▁▁▁▂▃▃▃▆▆▇█▃ beats 70/379avg 1268▇▇▇▇▇▇▇ 17%blunt
other tests5 not in a task · 65% of its score
testresultvs the others in its rundifficultycountswhy
BigCodeBench (Complete) lab41.0% ✎▂▁▁▄▂▅▇█▆▂▂▂ beats 30/58medium · avg 50%▇▇▇▇▇▇▇▇ 20%at its level
BigCodeBench (Instruct) lab31.8% ✎▃▂·▆▆██▆▅▃▃▃ beats 9/33medium · avg 41%▇▇▇▇▇▇▇▇ 20%at its level
GPQA Diamond30.7% ✎▁▁▁▁▃▄▆▄▅▇█▅ beats 19/208hard · avg 40%▇▇▇▇ 11%sharp
Polish EQ-Bench v2 (SpeakLeash)60.7% ✎▁··▁▁▂▂▆▅▆█▆ beats 41/70medium · avg 64%▇▇▇▇ 10%at its level
Open PT-LLM Leaderboard average (9 Portuguese tasks)74.8% ✎▃▁▁▁▁▁▁▁▂█▅▁ beats 223/276medium · avg 73%▇▇ 3.8%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 Qwen1.5 32B Chat · needs ~19.7 GB · from huggingface.co/Qwen (official)
    chat in the terminal
    llama cli -hf Qwen/Qwen1.5-32B-Chat-GGUF:q4_k_m
  3. Or start a local server and open the address it prints (http://localhost:9931)
    llama serve -hf Qwen/Qwen1.5-32B-Chat-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 Qwen1.5 32B Chat · needs ~19.7 GB · from huggingface.co/Qwen (official)

    open in LM Studio ↗

  3. Or download it in the terminal
    lms get https://huggingface.co/Qwen/Qwen1.5-32B-Chat-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 Qwen1.5 32B Chat · needs ~20.01 GB · from ollama.com
    chat in the terminal
    ollama run qwen:32b-chat

Official weights and documentation: huggingface.co/Qwen ↗

$ how the score was worked out · BigCodeBench paper (Zhuo et a… 40%, Polyrating: A Cost-Effective… 17%, LMArena leaderboard dataset 17% and 3 more

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
BigCodeBench paper (Zhuo et al., ICLR 2025), arXiv 2406.15877v4 · lab-reported2▇▇▇▇▇▇▇▇▇▇▇▇ 40%CC BY 4.0
Polyrating: A Cost-Effective and Bias-Aware Rating System for LLM Evaluation (arXiv:2409.00696v3)1▇▇▇▇▇ 17%CC-BY-4.0
LMArena leaderboard dataset1▇▇▇▇▇ 17%CC BY 4.0
Epoch AI — internal evaluations1▇▇▇ 11%CC BY 4.0
SpeakLeash Polish EQ-Bench leaderboard1▇▇▇ 10%Apache-2.0
Open Portuguese LLM Leaderboard (archived)1▇ 4%Apache-2.0
prior · pull toward the middle▇ 1%
weighted average= 44.0

$ 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