microsoft/phi-4-mini-reasoning

LM-STUDIO MLX

phi3 · 3.8B · 4bit

Good

Mar 3, 2026 · Apple M4

qwen3.6:35b-a3b-coding-nvfp4

OLLAMA GGUF

nvfp4

Not Rec.

May 25, 2026 · Apple M4 Pro

Global Score

62 vs 76

Hardware Fit

99 vs 77

Quality Score

46 vs 76

Hardware

microsoft/phi-4-mi… qwen3.6:35b-a3b-co…

MachineMacBook AirMacBook Pro

CPUApple M4Apple M4 Pro

Cores1014

RAM32 GB48 GB

GPUApple M4Apple M4 Pro

OSmacOS 26.3macOS 26.4.1

Archarm64arm64

Power Modebalancedbalanced

Performance

microsoft/phi-4-mi… qwen3.6:35b-a3b-co…

Tokens/sec40.372.7

First chunk289 ms147 ms

TTFT289 ms30.0 s

Load timeN/A5.7 s

Memory usage2.0 GB19.6 GB

Memory %6%41%

HW Fit Score Breakdown

microsoft/phi-4-mini-re…

Speed

50/50

TTFT

20/20

Memory

29/30

qwen3.6:35b-a3b-coding-…

Speed

50/50

TTFT

0/20

Memory

27/30

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

qwen3.6:35b-a3b-coding-…

Reasoning

19/20

Coding

9/20

Instruction

13/20

Structured

12/15

Math

13/15

Multilingual

10/10

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

View microsoft/phi-4-mi… details | View qwen3.6:35b-a3b-co… 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