Measured model
Measured on a Mac Studio (M5 Max, 36GB)gemma-4-E4B-it
Google · Ollama name hf.co/unsloth/gemma-4-E4B-it-GGUF:Q4_K_M
On a Mac Studio (M5 Max, 36GB), gemma-4-E4B-it answers a simple question in about 2.6 s, gets 79% of the Japanese knowledge questions right, 92% of the math problems, and uses 5.4GB of memory.
Results
| Measure | Result | Among measured models | Note |
|---|---|---|---|
| Reply time | about 2.6 s | 16 of 33 | Until one simple common-sense question is answered (median of 50) |
| Knowledge (high school to university) | 79% | 17 of 33 | 200 questions, ±6 |
| Math (word problems) | 92% | 20 of 33 | 100 questions, ±7 |
| Memory used | 5.4GB | 9 of 33 | |
| EN→JA translation | 32 pts | 10 of 30 | out of 100 (chrF), about 0.5 s a sentence |
| JA→EN translation | 55 pts | 16 of 30 | out of 100 (chrF), about 4.8 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/unsloth/gemma-4-E4B-it-GGUF:Q4_K_M
It used 5.4GB 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
- Size
- 7.52B parameters
- Quantization
- Q4_K_M
- Thinks before answering
- No
- Longest input at once
- 131,072 tokens
- Released (Hugging Face)
- Mar 2, 2026
- Generation speed
- 89.9 tok/s
- Start-up (loading)
- about 1.1 s
- Measured on
- Oct 10, 2026
- Ollama
- 0.34.3
- Hugging Face
- google/gemma-4-E4B-it
- Series
- Gemma
What the parts of a name mean (size, quantization and so on): how to read a model name.
Models of similar memory
- LFM2.5-8B-A1B (5.4GB of memory, knowledge 71%, reply about 1.7 s)
- Ornith-1.0-9B (6.2GB of memory, knowledge 85%, reply about 3.8 s)
- Ornith-1.5-9B (6.4GB of memory, knowledge 77%, reply about 2.5 s)
- DeepSeek-R1-0528-Qwen3-8B (6.4GB of memory, knowledge 72%, reply about 9.4 s)
- NVIDIA-Nemotron-3.5-Bolt-E4B-BF16 (6.5GB of memory, knowledge 76%, reply about 2.6 s)
Compare the main models on the text page. The series page lists every model measured.
Task recommendations and capabilities · Measurements by model