qwen3:4b

qwen3 · 4.0B · Q4_K_M

Marginal

Mar 1, 2026 · Apple M4

dolphin-phi:2.7b

phi2 · 3B · Q4_0

Good

Mar 1, 2026 · Apple M4

Global Score

48 vs 66

Hardware Fit

53 vs 100

Quality Score

45 vs 44

Hardware

qwen3:4b dolphin-phi:2.7b

Machine—MacBook Air

CPUApple M4Apple M4

Cores1010

RAM32 GB32 GB

GPUApple M4Apple M4

OSmacOS 26.3macOS 26.3

Archarm64arm64

Power Modeunknownbalanced

Performance

qwen3:4b dolphin-phi:2.7b

Tokens/sec11.356.1

TTFT9.2 s108 ms

Load time0.1 s0.4 s

Memory usage7.2 GB2.2 GB

Memory %23%7%

HW Fit Score Breakdown

qwen3:4b

Speed

17/40

TTFT

6/30

Memory

30/30

dolphin-phi:2.7b

Speed

40/40

TTFT

30/30

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

dolphin-phi:2.7b

Reasoning

10/20

Coding

6/20

Instruction

12/20

Structured

2/15

Math

9/15

Multilingual

5/10

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

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

Run yours and compare

npx metrillm@latest bench

Requires Node 20+ and Ollama or LM Studio running