microsoft/phi-4-mini-reasoning

LM-STUDIO MLX

phi3 · 3.8B · 4bit

Good

Mar 3, 2026 · Apple M4

gpt-oss-orchestrator:latest

OLLAMA GGUF

gptoss · 20.9B · MXFP4

Excellent

Mar 19, 2026 · Apple M4

Global Score

62 vs 88

Hardware Fit

99 vs 80

Quality Score

46 vs 91

Hardware

microsoft/phi-4-mi… gpt-oss-orchestrat…

MachineMacBook AirMac mini

CPUApple M4Apple M4

Cores1010

RAM32 GB24 GB

GPUApple M4Apple M4

OSmacOS 26.3macOS 26.3

Archarm64arm64

Power Modebalancedbalanced

Performance

microsoft/phi-4-mi… gpt-oss-orchestrat…

Tokens/sec40.324.6

First chunk289 ms525 ms

TTFT289 ms4.8 s

Load timeN/A8.5 s

Memory usage2.0 GB13.8 GB

Memory %6%58%

HW Fit Score Breakdown

microsoft/phi-4-mini-re…

Speed

50/50

TTFT

20/20

Memory

29/30

gpt-oss-orchestrator:la…

Speed

49/50

TTFT

10/20

Memory

21/30

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

gpt-oss-orchestrator:la…

Reasoning

19/20

Coding

19/20

Instruction

13/20

Structured

15/15

Math

15/15

Multilingual

10/10

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

View microsoft/phi-4-mi… details | View gpt-oss-orchestrat… 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