phi-1_5

LM-STUDIO GGUF

phi2 · Q8_0

Not Rec.

Mar 6, 2026 · Intel Core™ i5-5300U

gemma4:31b

OLLAMA GGUF

gemma4 · 31.3B · Q4_K_M

Not Rec.

Apr 13, 2026 · Apple M4 Max

Global Score

28 vs 76

Hardware Fit

66 vs 46

Quality Score

11 vs 89

Hardware

phi-1_5 gemma4:31b

MachineLENOVO 20BUS00700MacBook Pro

CPUIntel Core™ i5-5300UApple M4 Max

Cores416

RAM16 GB64 GB

GPUIntel(R) HD Graphics 5500Apple M4 Max

OSMicrosoft Windows 10 Professionnel 10.0.19045macOS 26.3.1

Archx64arm64

Power Modebalancedbalanced

Performance

phi-1_5 gemma4:31b

Tokens/sec6.922.4

First chunk3040 ms565 ms

TTFT3.0 s30.0 s

Load timeN/A6.9 s

Memory usage1.4 GB43.9 GB

Memory %9%69%

HW Fit Score Breakdown

phi-1_5

Speed

24/50

TTFT

16/20

Memory

26/30

gemma4:31b

Speed

30/50

TTFT

0/20

Memory

16/30

Quality

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

gemma4:31b

Reasoning

16/20

Coding

19/20

Instruction

16/20

Structured

15/15

Math

14/15

Multilingual

9/10

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

View phi-1_5 details | View gemma4:31b 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