mlx-community/quantized-gemma-2b-it
LM-STUDIO GGUFMar 5, 2026 · Apple M4
gemma4:12b-mlx
OLLAMA GGUFJul 4, 2026 · Apple M2 Pro
Global Score
45 vs 84
Hardware Fit
100 vs 82
Quality Score
21 vs 85
Hardware
mlx-community/quan… gemma4:12b-mlx
MachineMacBook AirMacBook Pro
CPUApple M4Apple M2 Pro
Cores1010
RAM32 GB16 GB
GPUApple M4Apple M2 Pro
OSmacOS 26.3macOS 26.5
Archarm64arm64
Power Modebalancedbalanced
Performance
mlx-community/quan… gemma4:12b-mlx
Tokens/sec44.427.2
First chunk336 ms732 ms
TTFT336 ms8.1 s
Load timeN/A3.5 s
Memory usage0.1 GB7.1 GB
Memory %0%44%
HW Fit Score Breakdown
mlx-community/quantized…
Speed
50/50
TTFT
20/20
Memory
30/30
gemma4:12b-mlx
Speed
50/50
TTFT
6/20
Memory
26/30
Quality
mlx-community/quantized…
Reasoning
4/20
Coding
1/20
Instruction
9/20
Structured
4/15
Math
2/15
Multilingual
1/10
Reasoning: Poor Coding: Poor Instruction Following: Weak Structured Output: Weak Math: Poor Multilingual: Poor
gemma4:12b-mlx
Reasoning
16/20
Coding
17/20
Instruction
13/20
Structured
15/15
Math
14/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Strong 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