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 8.8 s, gets 88% of the Japanese knowledge questions right, 89% of the math problems, and uses 22.3GB of memory.
These numbers are from before the method changed on Oct 2, 2026 (see how it was measured).
Results
| Measure | Result | Among measured models | Note |
|---|---|---|---|
| Reply time | about 8.8 s | 25 of 30 | Until one simple common-sense question is answered (median of 50) |
| Knowledge (high school to university) | 88% | 1 of 30 | 200 questions, ±5, 1 cut off (counted wrong) |
| Math (word problems) | 89% | 1 of 30 | 100 questions, ±8 |
| Memory used | 22.3GB | 28 of 30 | |
| EN→JA translation | 29 pts | 23 of 28 | out of 100 (chrF), about 28.9 s a sentence |
| JA→EN translation | 54 pts | 20 of 28 | out of 100 (chrF), about 23.4 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 qwen3.6:35b-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
- 97.8 tok/s
- Start-up (loading)
- about 7.1 s
- Measured on
- Oct 1, 2026
- Ollama
- 0.34.3
- Hugging Face
- Qwen/Qwen3.6-35B-A3B
- Series
- Qwen
Models of similar memory
- DeepSeek-R1-Distill-Qwen-32B (22.4GB of memory, knowledge 81%, reply about 16.8 s)
- NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 (22.7GB of memory, knowledge 77%, reply about 2 s)
- Ornith-1.5-35B-A3B (21.8GB of memory, knowledge 82%, reply about 1.9 s)
- Ornith-1.0-35B (21.6GB of memory, knowledge 88%, reply about 10.1 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.