tinyllama
OLLAMA GGUFMar 6, 2026 · Apple M4
gemma4:12b-mlx
OLLAMA GGUFAug 24, 2026 · Apple M1 Pro
Global Score
43 vs 71
Hardware Fit
100 vs 76
Quality Score
19 vs 69
Hardware
tinyllama gemma4:12b-mlx
MachineMacBook AirMacBook Pro
CPUApple M4Apple M1 Pro
Cores1010
RAM32 GB16 GB
GPUApple M4Apple M1 Pro
OSmacOS 26.3macOS 26.6.2
Archarm64arm64
Power Modebalancedbalanced
Performance
tinyllama gemma4:12b-mlx
Tokens/sec133.425.0
First chunk61 ms787 ms
TTFT61 ms30.0 s
Load time0.5 s4.0 s
Memory usage0.2 GB7.1 GB
Memory %1%45%
HW Fit Score Breakdown
tinyllama
Speed
50/50
TTFT
20/20
Memory
30/30
gemma4:12b-mlx
Speed
50/50
TTFT
0/20
Memory
26/30
Quality
tinyllama
Reasoning
2/20
Coding
2/20
Instruction
7/20
Structured
5/15
Math
0/15
Multilingual
3/10
Reasoning: Poor Coding: Poor Instruction Following: Weak Structured Output: Weak Math: Poor Multilingual: Weak
gemma4:12b-mlx
Reasoning
14/20
Coding
10/20
Instruction
9/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Adequate Coding: Adequate Instruction Following: Weak Structured Output: Strong Math: Adequate Multilingual: Strong
Run yours and compare
$
npm install -g metrillm@latest$
metrillmRequires Node 20+ and Ollama or LM Studio running
Or run without installing: npx metrillm@latest