qwen3:4b

qwen3 · 4.0B · Q4_K_M

Marginal

Mar 1, 2026 · Apple M4

phi4-mini

Not Rec.

Mar 1, 2026 · Apple M4

Global Score

48 vs 39

Hardware Fit

53 vs 66

Quality Score

45 vs 21

Hardware

qwen3:4b phi4-mini

Machine—MacBook Air

CPUApple M4Apple M4

Cores1010

RAM32 GB32 GB

GPUApple M4Apple M4

OSmacOS 26.3macOS 26.3

Archarm64arm64

Power Modeunknownbalanced

Performance

qwen3:4b phi4-mini

Tokens/sec11.321.8

TTFT9.2 s9.6 s

Load time0.1 s3.5 s

Memory usage7.2 GB0.0 GB

Memory %23%0%

HW Fit Score Breakdown

qwen3:4b

Speed

17/40

TTFT

6/30

Memory

30/30

phi4-mini

Speed

31/40

TTFT

5/30

Memory

30/30

Quality

qwen3:4b

Reasoning

4/20

Coding

6/20

Instruction

8/20

Structured

6/15

Math

12/15

Multilingual

9/10

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

phi4-mini

Reasoning

11/20

Coding

0/20

Instruction

0/20

Structured

0/15

Math

5/15

Multilingual

5/10

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

View qwen3:4b details | View phi4-mini details

Run yours and compare

npx metrillm@latest bench

Requires Node 20+ and Ollama or LM Studio running