phi-3.5-mini-instruct

LM-STUDIO MLX

phi3 · 4bit

Marginal

Mar 4, 2026 · Apple M4

qwen3:8b

OLLAMA GGUF

qwen3 · 8.2B · Q4_K_M

Marginal

Mar 2, 2026 · Apple M4

Global Score

55 vs 47

Hardware Fit

100 vs 67

Quality Score

36 vs 38

Hardware

phi-3.5-mini-instr… qwen3:8b

MachineMacBook AirMacBook Air

CPUApple M4Apple M4

Cores1010

RAM32 GB32 GB

GPUApple M4Apple M4

OSmacOS 26.3macOS 26.3

Archarm64arm64

Power Modebalancedbalanced

Performance

phi-3.5-mini-instr… qwen3:8b

Tokens/sec43.418.7

First chunk359 msN/A

TTFT359 ms12.1 s

Load timeN/A1.2 s

Memory usage2.0 GB9.5 GB

Memory %6%30%

HW Fit Score Breakdown

phi-3.5-mini-instruct

Speed

50/50

TTFT

20/20

Memory

30/30

qwen3:8b

Speed

31/50

TTFT

6/20

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

qwen3:8b

Reasoning

5/20

Coding

5/20

Instruction

4/20

Structured

12/15

Math

2/15

Multilingual

10/10

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

View phi-3.5-mini-instr… details | View qwen3:8b 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