gemma4:e4b-mlx

OLLAMA GGUF

Excellent

Jul 7, 2026 · Apple M2 Pro

phi-1_5

LM-STUDIO GGUF

phi2 · Q8_0

Not Rec.

Mar 6, 2026 · Intel Core™ i5-5300U

Global Score

85 vs 28

Hardware Fit

95 vs 66

Quality Score

81 vs 11

Hardware

gemma4:e4b-mlx phi-1_5

MachineMacBook ProLENOVO 20BUS00700

CPUApple M2 ProIntel Core™ i5-5300U

Cores104

RAM16 GB16 GB

GPUApple M2 ProIntel(R) HD Graphics 5500

OSmacOS 26.5Microsoft Windows 10 Professionnel 10.0.19045

Archarm64x64

Power Modebalancedbalanced

Performance

gemma4:e4b-mlx phi-1_5

Tokens/sec47.36.9

First chunk258 ms3040 ms

TTFT258 ms3.0 s

Load time5.1 sN/A

Memory usage7.9 GB1.4 GB

Memory %49%9%

HW Fit Score Breakdown

gemma4:e4b-mlx

Speed

50/50

TTFT

20/20

Memory

25/30

phi-1_5

Speed

24/50

TTFT

16/20

Memory

26/30

Quality

gemma4:e4b-mlx

Reasoning

15/20

Coding

18/20

Instruction

15/20

Structured

15/15

Math

8/15

Multilingual

10/10

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

phi-1_5

Reasoning

2/20

Coding

2/20

Instruction

3/20

Structured

0/15

Math

2/15

Multilingual

2/10

Reasoning: Poor Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Poor Multilingual: Poor

View gemma4:e4b-mlx details | View phi-1_5 details

Run yours and compare

$ npm install -g metrillm@latest

$ metrillm

Requires Node 20+ and Ollama or LM Studio running

Or run without installing: npx metrillm@latest