Measured model
Measured on a Mac Studio (M5 Max, 36GB)NVIDIA-Nemotron-Nano-12B-v2
NVIDIA · Ollama name hf.co/bartowski/nvidia_NVIDIA-Nemotron-Nano-12B-v2-GGUF:Q4_K_M
On a Mac Studio (M5 Max, 36GB), NVIDIA-Nemotron-Nano-12B-v2 answers a simple question in about 7.1 s, gets 79% of the Japanese knowledge questions right, 85% of the math problems, and uses 8.1GB 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 7.1 s | 24 of 30 | Until one simple common-sense question is answered (median of 50) |
| Knowledge (high school to university) | 79% | 11 of 30 | 200 questions, ±6, 1 cut off (counted wrong) |
| Math (word problems) | 85% | 9 of 30 | 100 questions, ±8, 1 cut off (counted wrong) |
| Memory used | 8.1GB | 13 of 30 | |
| EN→JA translation | 31 pts | 19 of 28 | out of 100 (chrF), about 11.9 s a sentence |
| JA→EN translation | 54 pts | 19 of 28 | out of 100 (chrF), about 10.2 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 hf.co/bartowski/nvidia_NVIDIA-Nemotron-Nano-12B-v2-GGUF:Q4_K_M
It used 8.1GB here. To use it comfortably alongside other apps, a Mac with 24GB of memory or more is a good guide (the model then takes about half the memory).
About the model
- Maker
- NVIDIA
- Size
- 12.3B parameters
- Quantization
- Q4_K_M
- Thinks before answering
- Yes
- Longest input at once
- 1,048,576 tokens
- Released (Hugging Face)
- Aug 21, 2025
- Generation speed
- 44.4 tok/s
- Start-up (loading)
- about 0.8 s
- Measured on
- Sep 30, 2026
- Ollama
- 0.34.3
- Hugging Face
- nvidia/NVIDIA-Nemotron-Nano-12B-v2
- Series
- Nemotron
Models of similar memory
- GLM-4-9B-0414 (6.7GB of memory, knowledge 66%, reply about 0.1 s)
- 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)
- Ministral-3-14B-Instruct-2512 (9.9GB of memory, knowledge 72%, reply about 0.1 s)
- Ornith-1.0-9B (6.2GB of memory, knowledge 83%, reply about 3.6 s)
Compare the main models on the text page. The series page lists every model measured.