phi-3.5-mini-instruct

LM-STUDIO MLX

phi3 · 4bit

Marginal

Mar 4, 2026 · Apple M4

qwen2.5:14b

OLLAMA GGUF

qwen2 · 14.8B · Q4_K_M

Excellent

Sep 15, 2026 · Intel Core™ i5-14400F

Global Score

55 vs 90

Hardware Fit

100 vs 100

Quality Score

36 vs 85

Hardware

phi-3.5-mini-instr… qwen2.5:14b

MachineMacBook AirGigabyte Technology Co., Ltd. B760 AORUS ELITE AX DDR4

CPUApple M4Intel Core™ i5-14400F

Cores1016

RAM32 GB32 GB

GPUApple M4NVIDIA GeForce RTX 5060 Ti

OSmacOS 26.3Microsoft Windows 11 Professionnel 10.0.26200

Archarm64x64

Power Modebalancedbalanced

Performance

phi-3.5-mini-instr… qwen2.5:14b

Tokens/sec43.437.8

First chunk359 ms74 ms

TTFT359 ms74 ms

Load timeN/A6.2 s

Memory usage2.0 GB8.8 GB

Memory %6%28%

HW Fit Score Breakdown

phi-3.5-mini-instruct

Speed

50/50

TTFT

20/20

Memory

30/30

qwen2.5:14b

Speed

50/50

TTFT

20/20

Memory

30/30

Quality

phi-3.5-mini-instruct

Reasoning

11/20

Coding

4/20

Instruction

7/20

Structured

1/15

Math

7/15

Multilingual

6/10

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

qwen2.5:14b

Reasoning

17/20

Coding

18/20

Instruction

14/20

Structured

15/15

Math

11/15

Multilingual

10/10

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

View phi-3.5-mini-instr… details | View qwen2.5:14b 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