qwen3:8b

qwen3 · 8.2B · Q4_K_M

Marginal

Mar 2, 2026 · Apple M4

qwen3:4b

qwen3 · 4.0B · Q4_K_M

Marginal

Mar 1, 2026 · Apple M4

Global Score

50 vs 48

Hardware Fit

67 vs 53

Quality Score

38 vs 45

Hardware

qwen3:8b qwen3:4b

MachineMacBook Air—

CPUApple M4Apple M4

Cores1010

RAM32 GB32 GB

GPUApple M4Apple M4

OSmacOS 26.3macOS 26.3

Archarm64arm64

Power Modebalancedunknown

Performance

qwen3:8b qwen3:4b

Tokens/sec18.711.3

TTFT12.1 s9.2 s

Load time1.2 s0.1 s

Memory usage9.5 GB7.2 GB

Memory %30%23%

HW Fit Score Breakdown

qwen3:8b

Speed

31/40

TTFT

6/30

Memory

30/30

qwen3:4b

Speed

17/40

TTFT

6/30

Memory

30/30

Quality

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

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 qwen3:8b details | View qwen3:4b details

Run yours and compare

npx metrillm@latest bench

Requires Node 20+ and Ollama or LM Studio running