microsoft/phi-4-mini-reasoning

LM-STUDIO MLX

phi3 · 3.8B · 4bit

Good

Mar 3, 2026 · Apple M4

qwen3:1.7b

OLLAMA GGUF

qwen3 · 2.0B · Q4_K_M

Good

Oct 11, 2026 · AMD Ryzen 5 5500

Global Score

62 vs 79

Hardware Fit

99 vs 100

Quality Score

46 vs 70

Hardware

microsoft/phi-4-mi… qwen3:1.7b

MachineMacBook AirMicrosoft WSL

CPUApple M4AMD Ryzen 5 5500

Cores1012

RAM32 GB8 GB

GPUApple M4Integrated / Unknown

OSmacOS 26.3Ubuntu 26.04.1 LTS

Archarm64x64

Power Modebalancedunknown

Performance

microsoft/phi-4-mi… qwen3:1.7b

Tokens/sec40.3188.0

First chunk289 ms108 ms

TTFT289 ms1.2 s

Load timeN/A7.5 s

Memory usage2.0 GB1.6 GB

Memory %6%21%

HW Fit Score Breakdown

microsoft/phi-4-mini-re…

Speed

50/50

TTFT

20/20

Memory

29/30

qwen3:1.7b

Speed

50/50

TTFT

20/20

Memory

30/30

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

qwen3:1.7b

Reasoning

16/20

Coding

7/20

Instruction

14/20

Structured

15/15

Math

8/15

Multilingual

10/10

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

View microsoft/phi-4-mi… details | View qwen3:1.7b 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