qwen3.8:27b measured on a Mac Studio (M5 Max, 36GB)

Results

Measure	Result	Among measured models	Note
Reply time	about 6.9 s	23 of 30	Until one simple common-sense question is answered (median of 50)
Knowledge (high school to university)	85%	3 of 30	200 questions, ±6
Math (word problems)	89%	1 of 30	100 questions, ±8
Memory used	18.2GB	21 of 30
EN→JA translation	31 pts	17 of 28	out of 100 (chrF), about 22 s a sentence
JA→EN translation	58 pts	2 of 28	out of 100 (chrF), about 20 s a sentence

"Among measured models" is the place among the 30 models measured on this site (lower is better for time and memory).

Try it on your Mac

Install the Mac version of Ollama from ollama.com and start it.
Type this in Terminal. The first time, the model downloads; then you can chat with it.ollama run qwen3.8:27b

It used 18.2GB 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: 27.3B parameters
Quantization: Q4_K_M
Thinks before answering: Yes
Longest input at once: 262,144 tokens
Released (Hugging Face): Aug 5, 2026
Generation speed: 29.6 tok/s
Start-up (loading): about 5.9 s
Measured on: Sep 26, 2026
Ollama: 0.34.3
Hugging Face: Qwen/Qwen3.8-27B
Series: Qwen

Models of similar memory

gemma3:27b (18.4GB of memory, knowledge 74%, reply about 0.4 s)
muse-glimmer:30b (17.6GB of memory, knowledge 85%, reply about 14.3 s)
gemma4:26b (18.7GB of memory, knowledge 82%, reply about 2.9 s)
qwen3-coder:30b (19.4GB of memory, knowledge 68%, reply about 0.1 s)
glm-4.7-flash:latest (19.5GB of memory, knowledge 77%, reply about 6.3 s)

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