phi-3-mini-128k-instruct
LM-STUDIO MLXphi3 · 4bit
Mar 4, 2026 · Apple M4
gemma4:12b-mlx
OLLAMA GGUFAug 24, 2026 · Apple M1 Pro
Global Score
38 vs 71
Hardware Fit
100 vs 76
Quality Score
12 vs 69
Hardware
phi-3-mini-128k-in… 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
phi-3-mini-128k-in… gemma4:12b-mlx
Tokens/sec44.025.0
First chunk384 ms787 ms
TTFT385 ms30.0 s
Load timeN/A4.0 s
Memory usage2.0 GB7.1 GB
Memory %6%45%
HW Fit Score Breakdown
phi-3-mini-128k-instruct
Speed
50/50
TTFT
20/20
Memory
30/30
gemma4:12b-mlx
Speed
50/50
TTFT
0/20
Memory
26/30
Quality
phi-3-mini-128k-instruct
Reasoning
3/20
Coding
2/20
Instruction
2/20
Structured
1/15
Math
2/15
Multilingual
2/10
Reasoning: Poor Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Poor Multilingual: Poor
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