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
| Measure | Result | Among measured models | Note |
|---|---|---|---|
| Reply time | about 8.5 s | 27 of 33 | Until one simple common-sense question is answered (median of 50) |
| Knowledge (high school to university) | 87% | 2 of 33 | 200 questions, ±5 |
| Math (word problems) | 98% | 3 of 33 | 100 questions, ±5 |
| Memory used | 22.3GB | 31 of 33 | |
| EN→JA translation | 29 pts | 23 of 30 | out of 100 (chrF), about 28.9 s a sentence |
| JA→EN translation | 54 pts | 19 of 30 | out 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
- 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 qwen3.6:35b-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
- DeepSeek-R1-Distill-Qwen-32B (22.4GB of memory, knowledge 81%, reply about 17.9 s)
- NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 (22.7GB of memory, knowledge 80%, reply about 3.7 s)
- Ornith-1.5-35B-A3B (21.8GB of memory, knowledge 83%, reply about 2.5 s)
- Ornith-1.0-35B (21.6GB of memory, knowledge 89%, reply about 9.1 s)
- glm-4.7-flash:latest (19.4GB of memory, knowledge 76%, reply about 7.5 s)
Compare the main models on the text page. The series page lists every model measured.
Task recommendations and capabilities · Measurements by model