Measured model
Measured on a Mac Studio (M5 Max, 36GB)Ornith-1.5-35B-A3B
ornith-ai · Ollama name hf.co/ornith-ai/Ornith-1.5-35B-A3B-GGUF:Q4_K_M
On a Mac Studio (M5 Max, 36GB), Ornith-1.5-35B-A3B answers a simple question in about 2.5 s, gets 83% of the Japanese knowledge questions right, 97% of the math problems, and uses 21.8GB of memory.
Results
| Measure | Result | Among measured models | Note |
|---|---|---|---|
| Reply time | about 2.5 s | 14 of 33 | Until one simple common-sense question is answered (median of 50) |
| Knowledge (high school to university) | 83% | 8 of 33 | 200 questions, ±6, 3 cut off (counted wrong) |
| Math (word problems) | 97% | 8 of 33 | 100 questions, ±6 |
| Memory used | 21.8GB | 30 of 33 | |
| EN→JA translation | 32 pts | 14 of 30 | out of 100 (chrF), about 2.5 s a sentence |
| JA→EN translation | 57 pts | 6 of 30 | out of 100 (chrF), about 2.9 s a sentence |
"Among measured models" is the place among the 33 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/ornith-ai/Ornith-1.5-35B-A3B-GGUF:Q4_K_M
It used 21.8GB 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
- ornith-ai
- Size
- 35.5B parameters
- Quantization
- Q4_K_M
- Thinks before answering
- Yes
- Longest input at once
- 262,144 tokens
- Released (Hugging Face)
- Aug 18, 2026
- Generation speed
- 98.2 tok/s
- Start-up (loading)
- about 1.6 s
- Measured on
- Oct 10, 2026
- Ollama
- 0.34.3
- Hugging Face
- ornith-ai/Ornith-1.5-35B-A3B
- Series
- Ornith
What the parts of a name mean (size, quantization and so on): how to read a model name.
Models of similar memory
- Ornith-1.0-35B (21.6GB of memory, knowledge 89%, reply about 9.1 s)
- qwen3.6:35b-a3b (22.3GB of memory, knowledge 87%, reply about 8.5 s)
- 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)
- 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