gemma2:9b

gemma2 · 9.2B · Q4_0

MacBook Air (Apple M4)

32 GB · macOS 26.3

Tested on March 1, 2026

Top 44% Compare

Global Score

69 /100

Good

Hardware Fit

89/100

Quality

56/100

Get this model

🦙

Ollama

ollama pull gemma2:9b

View on Ollama Library

ollama.com/library/gemma2

🤗

Find on HuggingFace

GGUF versions & quantizations

Hardware

Machine: MacBook Air
CPU: Apple M4
Cores: 10 total (4 perf + 6 eff)
Frequency: 2.4 GHz
RAM: 32 GB LPDDR5
GPU: Apple M4
OS: macOS 26.3
Arch: arm64
Power Mode: balanced

Performance

Tokens/sec Tokens generated per second — higher is better: 16.8
Standard deviation Variation of speed across benchmark runs — lower means more consistent: ±0.7
Time to first token How fast the model starts responding — lower is better: 372 ms
Load time Time to load the model into memory before inference: 0.8 s
Memory usage RAM consumed during inference — percentage of total system memory: 8.2 GB (26%)
Total tokens Total number of tokens generated across all benchmark prompts: 964

Score breakdown

Speed

29/40

Time to first token

30/30

Memory

30/30

Quality

Reasoning

11/20

Coding

0/20

Instruction following

13/20

Structured output

15/15

Math

7/15

Multilingual

10/10

Category levels

Reasoning: Adequate Coding: Poor Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong

Metadata

Spec version: 0.2.0
Runtime: Ollama 0.17.4
Model format: GGUF
Hardware profile: BALANCED
Result hash: 3e8f770f2c3fb3effd23eb0eb606d413a55c78ebaeddbb3a7316be4faca4800b

Interpretation

Hardware fit: 89/100. Overall suitability: GOOD (Global 69/100). Category profile: Reasoning: Adequate, Coding: Poor, Instruction Following: Adequate, Structured Output: Strong, Math: Weak, Multilingual: Strong.

Run yours now

npx metrillm@latest bench

Requires Node 20+ and Ollama running