gemma3:1b

gemma3 · 999.89M · Q4_K_M

MacBook Air (Apple M4)

32 GB · macOS 26.3

Tested on February 28, 2026

Top 31% Compare

Global Score

72 /100

Good

Hardware Fit

98/100

Quality

55/100

Get this model

🦙

Ollama

ollama pull gemma3:1b

View on Ollama Library

ollama.com/library/gemma3

🤗

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

Performance

Tokens/sec Tokens generated per second — higher is better: 39.5
Standard deviation Variation of speed across benchmark runs — lower means more consistent: ±0.9
Time to first token How fast the model starts responding — lower is better: 333 ms
Load time Time to load the model into memory before inference: 1.6 s
Memory usage RAM consumed during inference — percentage of total system memory: 1.3 GB (4%)
Total tokens Total number of tokens generated across all benchmark prompts: 990

Score breakdown

Speed

40/40

Time to first token

30/30

Memory

28/30

Quality

Reasoning

6/20

Coding

13/20

Instruction following

15/20

Structured output

12/15

Math

1/15

Multilingual

8/10

Category levels

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

Metadata

Spec version: 0.1.0
Runtime: Ollama 0.17.4
Model format: GGUF
Hardware profile: BALANCED
Result hash: 3add497089bfe3917998e87399985454710337c9d70928c918831f45497cbac2

Interpretation

Hardware fit: 98/100. Overall suitability: GOOD (Global 72/100). Category profile: Reasoning: Weak, Coding: Adequate, Instruction Following: Strong, Structured Output: Strong, Math: Poor, Multilingual: Strong.

Run yours now

npx metrillm@latest bench

Requires Node 20+ and Ollama running