microsoft/phi-4-mini-reasoning

LM-STUDIO MLX

phi3 · 3.8B · 4bit

Good

Mar 3, 2026 · Apple M4

qwen3.5:35b-a3b-q4_K_M

OLLAMA GGUF

qwen35moe · 36.0B · Q4_K_M

Not Rec.

Jul 30, 2026 · Intel Xeon® E5-2637 v3

Global Score

62 vs 49

Hardware Fit

99 vs 54

Quality Score

46 vs 47

Hardware

microsoft/phi-4-mi… qwen3.5:35b-a3b-q4…

MachineMacBook AirDell Inc. Precision Tower 7910

CPUApple M4Intel Xeon® E5-2637 v3

Cores1016

RAM32 GB96 GB

GPUApple M4NVIDIA GeForce RTX 5060 Ti

OSmacOS 26.3Microsoft Windows 10 Pro 10.0.19045

Archarm64x64

Power Modebalancedbalanced

Performance

microsoft/phi-4-mi… qwen3.5:35b-a3b-q4…

Tokens/sec40.321.6

First chunk289 ms1505 ms

TTFT289 ms30.0 s

Load timeN/A53.8 s

Memory usage2.0 GB22.7 GB

Memory %6%24%

HW Fit Score Breakdown

microsoft/phi-4-mini-re…

Speed

50/50

TTFT

20/20

Memory

29/30

qwen3.5:35b-a3b-q4_K_M

Speed

24/50

TTFT

0/20

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

qwen3.5:35b-a3b-q4_K_M

Reasoning

14/20

Coding

1/20

Instruction

6/20

Structured

5/15

Math

11/15

Multilingual

10/10

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

View microsoft/phi-4-mi… details | View qwen3.5:35b-a3b-q4… 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