Measured model
Measured on a Mac Studio (M5 Max, 36GB)Qwen3.5-9B
Alibaba · Ollama name hf.co/unsloth/Qwen3.5-9B-GGUF:Q4_K_M
On a Mac Studio (M5 Max, 36GB), Qwen3.5-9B answers a simple question in about 40.3 s, gets 84% of the Japanese knowledge questions right, 87% of the math problems, and uses 6.5GB of memory.
Results
| Measure | Result | Among measured models | Note |
|---|---|---|---|
| Reply time | about 40.3 s | 32 of 32 | Until one simple common-sense question is answered (median of 50) |
| Knowledge (high school to university) | 84% | 6 of 32 | 200 questions, ±6, 2 cut off (counted wrong) |
| Math (word problems) | 87% | 8 of 32 | 100 questions, ±8 |
| Memory used | 6.5GB | 12 of 32 | |
| EN→JA translation | Timed out | — | Did not finish within the time limit |
| JA→EN translation | Timed out | — | Did not finish within the time limit |
"Among measured models" is the place among the 32 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 hf.co/unsloth/Qwen3.5-9B-GGUF:Q4_K_M
It used 6.5GB here. To use it comfortably alongside other apps, a Mac with 16GB of memory or more is a good guide (the model then takes about half the memory).
About the model
- Maker
- Alibaba
- Size
- 8.95B parameters
- Quantization
- Q4_K_M
- Thinks before answering
- Yes
- Longest input at once
- 262,144 tokens
- Released (Hugging Face)
- Feb 27, 2026
- Generation speed
- 64.2 tok/s
- Start-up (loading)
- about 1.1 s
- Measured on
- Oct 3, 2026
- Ollama
- 0.34.3
- Hugging Face
- Qwen/Qwen3.5-9B
- 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-R1-0528-Qwen3-8B (6.4GB of memory, knowledge 73%, reply about 9.8 s)
- Ornith-1.5-9B (6.4GB of memory, knowledge 78%, reply about 2.5 s)
- GLM-4-9B-0414 (6.7GB of memory, knowledge 66%, reply about 0.1 s)
- Ornith-1.0-9B (6.2GB of memory, knowledge 83%, reply about 3.6 s)
- gemma-4-E4B-it (5.4GB of memory, knowledge 82%, reply about 4 s)
Compare the main models on the text page. The series page lists every model measured.