phi:2.7b

phi2 · 3B · Q4_0

Good

Mar 2, 2026 · Apple M4

qwen3:4b

qwen3 · 4.0B · Q4_K_M

Marginal

Mar 1, 2026 · Apple M4

Global Score

65 vs 48

Hardware Fit

100 vs 53

Quality Score

41 vs 45

Hardware

phi:2.7b qwen3:4b

MachineMacBook Air—

CPUApple M4Apple M4

Cores1010

RAM32 GB32 GB

GPUApple M4Apple M4

OSmacOS 26.3macOS 26.3

Archarm64arm64

Power Modebalancedunknown

Performance

phi:2.7b qwen3:4b

Tokens/sec56.611.3

TTFT110 ms9.2 s

Load time0.4 s0.1 s

Memory usage2.2 GB7.2 GB

Memory %7%23%

HW Fit Score Breakdown

phi:2.7b

Speed

40/40

TTFT

30/30

Memory

30/30

qwen3:4b

Speed

17/40

TTFT

6/30

Memory

30/30

Quality

phi:2.7b

Reasoning

7/20

Coding

4/20

Instruction

9/20

Structured

11/15

Math

8/15

Multilingual

2/10

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

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

View phi:2.7b details | View qwen3:4b details

Run yours and compare

npx metrillm@latest bench

Requires Node 20+ and Ollama or LM Studio running