Measured model

Measured on a Mac Studio (M5 Max, 36GB)qwen3.6:35b-a3b

Alibaba

On a Mac Studio (M5 Max, 36GB), qwen3.6:35b-a3b answers a simple question in about 8.5 s, gets 87% of the Japanese knowledge questions right, 98% of the math problems, and uses 22.3GB of memory.

Results

MeasureResultAmong measured modelsNote
Reply timeabout 8.5 s27 of 33Until one simple common-sense question is answered (median of 50)
Knowledge (high school to university)87%2 of 33200 questions, ±5
Math (word problems)98%3 of 33100 questions, ±5
Memory used22.3GB31 of 33
EN→JA translation29 pts23 of 30out of 100 (chrF), about 28.9 s a sentence
JA→EN translation54 pts19 of 30out of 100 (chrF), about 23.4 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 qwen3.6:35b-a3b

It used 22.3GB 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
35.5B parameters
Quantization
Q4_K_M
Thinks before answering
Yes
Longest input at once
262,144 tokens
Released (Hugging Face)
Apr 15, 2026
Generation speed
125.7 tok/s
Start-up (loading)
about 8.1 s
Measured on
Nov 2, 2026
Ollama
0.34.3
Hugging Face
Qwen/Qwen3.6-35B-A3B
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