Measured model

Measured on a Mac Studio (M5 Max, 36GB)qwen3-coder:30b

Alibaba

On a Mac Studio (M5 Max, 36GB), qwen3-coder:30b answers a simple question in about 0.1 s, gets 69% of the Japanese knowledge questions right, 89% of the math problems, and uses 19.4GB of memory.

Results

MeasureResultAmong measured modelsNote
Reply timeabout 0.1 s1 of 33Until one simple common-sense question is answered (median of 50)
Knowledge (high school to university)69%29 of 33200 questions, ±7
Math (word problems)89%23 of 33100 questions, ±8
Memory used19.4GB27 of 33
EN→JA translation31 pts19 of 30out of 100 (chrF), about 0.4 s a sentence
JA→EN translation55 pts17 of 30out of 100 (chrF), about 0.3 s a sentence

"Among measured models" is the place among the 33 models measured on this site (lower is better for time and memory).

Measured on other Macs

The numbers and places on this page come from the Mac above alone.

Try it on your Mac

  1. Install the Mac version of Ollama from ollama.com and start it.
  2. Type this in Terminal. The first time, the model downloads; then you can chat with it.ollama run qwen3-coder:30b

It used 19.4GB here. To use it comfortably alongside other apps, a Mac with 48GB of memory or more is a good guide (the model then takes about half the memory).

About the model

Maker
Alibaba
Size
30.5B parameters
Quantization
Q4_K_M
Thinks before answering
No
Longest input at once
262,144 tokens
Released (Hugging Face)
Jul 31, 2025
Generation speed
107.7 tok/s
Start-up (loading)
about 5.6 s
Measured on
Nov 2, 2026
Ollama
0.34.3
Hugging Face
Qwen/Qwen3-Coder-30B-A3B-Instruct
Series
Qwen

What the parts of a name mean (size, quantization and so on): how to read a model name.

Models of similar memory

Compare the main models on the text page. The series page lists every model measured.

Task recommendations and capabilities · Measurements by model