gemma4:12b-it-qat

gemma4 · 11.9B · Q4_0

THINKING MODEL

Mac mini (Apple M4 Pro)

24 GB · macOS 15.6.1

Tested on June 25, 2026

Top 8% Compare

Global Score

88 /100

Excellent

Hardware Fit

86/100

Quality

89/100

Get this model

🦙

Ollama

ollama pull gemma4:12b-it-qat

View on Ollama Library

ollama.com/library/gemma4

Get it in LM Studio

Search and download models directly from the app

🤗

Find on HuggingFace

GGUF versions & quantizations

Hardware

Machine: Mac mini
CPU: Apple M4 Pro
Cores: 12 total (8 perf + 4 eff)
Frequency: 2.4 GHz
RAM: 24 GB LPDDR5
GPU: Apple M4 Pro
OS: macOS 15.6.1
Arch: arm64
Power Mode: balanced

Performance

Tokens/sec Tokens generated per second — higher is better: 30.0
Standard deviation Variation of speed across benchmark runs — lower means more consistent: ±0.0
First chunk latency Delay before the first streamed chunk arrives from runtime: 686 ms
Time to first token How fast the model starts responding — lower is better: 7.1 s
Load time Time to load the model into memory before inference: 5.4 s
Memory usage RAM consumed during inference — percentage of total system memory: 7.1 GB (30%)
Total tokens Total number of tokens generated across all benchmark prompts: 1460
Thinking tokens (est.) Estimated internal reasoning tokens — models with "thinking" generate more tokens: ~735

Score breakdown

Speed

50/50

Time to first token

6/20

Memory

30/30

Quality

Reasoning

18/20

Coding

18/20

Instruction following

14/20

Structured output

15/15

Math

14/15

Multilingual

10/10

Category levels

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

Metadata

Spec version: 0.2.1
Runtime: Ollama 0.30.10
Model format: GGUF
Hardware profile: BALANCED
Result hash: faaef32833d16439cf58b65dc3cfc2f081d97b46585a6b505dd0a837e316762f

Interpretation

Hardware fit: 86/100. Overall suitability: EXCELLENT (Global 88/100). Category profile: Reasoning: Strong, Coding: Strong, Instruction Following: Adequate, Structured Output: Strong, Math: Strong, Multilingual: Strong.

Bench Environment

Power: AC CPU load: avg 5% (peak 7%)

Run yours now

$ npm install -g metrillm@latest

$ metrillm

Requires Node 20+ and Ollama or LM Studio running

Or run without installing: npx metrillm@latest