phi-3.5-mini-instruct

LM-STUDIO MLX

phi3 · 4bit

Marginal

Mar 4, 2026 · Apple M4

gemma4:e4b-mlx

OLLAMA GGUF

Excellent

Jul 7, 2026 · Apple M2 Pro

Global Score

55 vs 85

Hardware Fit

100 vs 95

Quality Score

36 vs 81

Hardware

phi-3.5-mini-instr… gemma4:e4b-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

phi-3.5-mini-instr… gemma4:e4b-mlx

Tokens/sec43.447.3

First chunk359 ms258 ms

TTFT359 ms258 ms

Load timeN/A5.1 s

Memory usage2.0 GB7.9 GB

Memory %6%49%

HW Fit Score Breakdown

phi-3.5-mini-instruct

Speed

50/50

TTFT

20/20

Memory

30/30

gemma4:e4b-mlx

Speed

50/50

TTFT

20/20

Memory

25/30

Quality

phi-3.5-mini-instruct

Reasoning

11/20

Coding

4/20

Instruction

7/20

Structured

1/15

Math

7/15

Multilingual

6/10

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

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

View phi-3.5-mini-instr… details | View gemma4:e4b-mlx 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