google/gemma-3-4b

LM-STUDIO MLX

gemma3 · 4B · 4bit

Good

Mar 3, 2026 · Apple M4

dolphin-phi:2.7b

OLLAMA GGUF

phi2 · 3B · Q4_0

Good

Mar 1, 2026 · Apple M4

Global Score

76 vs 61

Hardware Fit

100 vs 100

Quality Score

66 vs 44

Hardware

google/gemma-3-4b dolphin-phi:2.7b

MachineMacBook AirMacBook Air

CPUApple M4Apple M4

Cores1010

RAM32 GB32 GB

GPUApple M4Apple M4

OSmacOS 26.3macOS 26.3

Archarm64arm64

Power Modebalancedbalanced

Performance

google/gemma-3-4b dolphin-phi:2.7b

Tokens/sec39.456.1

First chunk468 msN/A

TTFT468 ms108 ms

Load timeN/A0.4 s

Memory usage2.8 GB2.2 GB

Memory %9%7%

HW Fit Score Breakdown

google/gemma-3-4b

Speed

50/50

TTFT

20/20

Memory

30/30

dolphin-phi:2.7b

Speed

40/50

TTFT

30/20

Memory

30/30

Quality

google/gemma-3-4b

Reasoning

10/20

Coding

17/20

Instruction

13/20

Structured

12/15

Math

4/15

Multilingual

10/10

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

dolphin-phi:2.7b

Reasoning

10/20

Coding

6/20

Instruction

12/20

Structured

2/15

Math

9/15

Multilingual

5/10

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

View google/gemma-3-4b details | View dolphin-phi:2.7b 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