qwen3:8b

qwen3 · 8.2B · Q4_K_M

Marginal

Mar 1, 2026 · Apple M4

phi4-mini

Not Rec.

Mar 1, 2026 · Apple M4

Global Score

42 vs 38

Hardware Fit

60 vs 64

Quality Score

30 vs 21

Hardware

qwen3:8b phi4-mini

MachineMacBook Air—

CPUApple M4Apple M4

Cores1010

RAM32 GB32 GB

GPUApple M4Apple M4

OSmacOS 26.3macOS 26.3

Archarm64arm64

Power Modeunknownbalanced

Performance

qwen3:8b phi4-mini

Tokens/sec18.221.7

TTFT12.4 s11.9 s

Load time2.7 s3.5 s

Memory usage9.5 GB0.0 GB

Memory %30%0%

HW Fit Score Breakdown

qwen3:8b

Speed

27/40

TTFT

3/30

Memory

30/30

phi4-mini

Speed

31/40

TTFT

3/30

Memory

30/30

Quality

qwen3:8b

Reasoning

9/20

Coding

0/20

Instruction

5/20

Structured

4/15

Math

3/15

Multilingual

9/10

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

View qwen3:8b details | View phi4-mini details

Run yours and compare

npx metrillm@latest bench

Requires Node 20+ and Ollama or LM Studio running