microsoft/phi-4-mini-reasoning

LM-STUDIO MLX

phi3 · 3.8B · 4bit

Good

Mar 3, 2026 · Apple M4

qwen3.5:4b

OLLAMA GGUF

qwen35 · 4.7B · Q4_K_M

Good

Aug 26, 2026 · Apple M1 Pro

Global Score

62 vs 68

Hardware Fit

99 vs 86

Quality Score

46 vs 60

Hardware

microsoft/phi-4-mi… qwen3.5:4b

MachineMacBook AirMacBook Pro

CPUApple M4Apple M1 Pro

Cores1010

RAM32 GB16 GB

GPUApple M4Apple M1 Pro

OSmacOS 26.3macOS 26.6.2

Archarm64arm64

Power Modebalancedbalanced

Performance

microsoft/phi-4-mi… qwen3.5:4b

Tokens/sec40.336.5

First chunk289 ms207 ms

TTFT289 ms6.6 s

Load timeN/A3.2 s

Memory usage2.0 GB5.3 GB

Memory %6%33%

HW Fit Score Breakdown

microsoft/phi-4-mini-re…

Speed

50/50

TTFT

20/20

Memory

29/30

qwen3.5:4b

Speed

50/50

TTFT

7/20

Memory

29/30

Quality

microsoft/phi-4-mini-re…

Reasoning

7/20

Coding

6/20

Instruction

7/20

Structured

7/15

Math

12/15

Multilingual

7/10

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

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 microsoft/phi-4-mi… 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