phi-1_5

LM-STUDIO GGUF

phi2 · Q8_0

Not Rec.

Mar 6, 2026 · Intel Core™ i5-5300U

qwen3.5:4b

OLLAMA GGUF

qwen35 · 4.7B · Q4_K_M

Good

Aug 26, 2026 · Apple M1 Pro

Global Score

28 vs 68

Hardware Fit

66 vs 86

Quality Score

11 vs 60

Hardware

phi-1_5 qwen3.5:4b

MachineLENOVO 20BUS00700MacBook Pro

CPUIntel Core™ i5-5300UApple M1 Pro

Cores410

RAM16 GB16 GB

GPUIntel(R) HD Graphics 5500Apple M1 Pro

OSMicrosoft Windows 10 Professionnel 10.0.19045macOS 26.6.2

Archx64arm64

Power Modebalancedbalanced

Performance

phi-1_5 qwen3.5:4b

Tokens/sec6.936.5

First chunk3040 ms207 ms

TTFT3.0 s6.6 s

Load timeN/A3.2 s

Memory usage1.4 GB5.3 GB

Memory %9%33%

HW Fit Score Breakdown

phi-1_5

Speed

24/50

TTFT

16/20

Memory

26/30

qwen3.5:4b

Speed

50/50

TTFT

7/20

Memory

29/30

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

qwen3.5:4b

Reasoning

16/20

Coding

1/20

Instruction

12/20

Structured

9/15

Math

12/15

Multilingual

10/10

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

View phi-1_5 details | View qwen3.5:4b 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