qwen3:0.6b

qwen3 · 751.63M · Q4_K_M

Good

Mar 2, 2026 · Apple M4

qwen3.5:0.8b

qwen35 · 873.44M · Q8_0

Good

Mar 2, 2026 · Apple M4

Global Score

77 vs 70

Hardware Fit

100 vs 99

Quality Score

62 vs 51

Hardware

qwen3:0.6b qwen3.5:0.8b

MachineMacBook AirMacBook Air

CPUApple M4Apple M4

Cores1010

RAM32 GB32 GB

GPUApple M4Apple M4

OSmacOS 26.3macOS 26.3

Archarm64arm64

Power Modebalancedbalanced

Performance

qwen3:0.6b qwen3.5:0.8b

Tokens/sec145.248.2

TTFT1.4 s195 ms

Load time0.7 s1.0 s

Memory usage4.1 GB2.5 GB

Memory %13%8%

HW Fit Score Breakdown

qwen3:0.6b

Speed

40/40

TTFT

30/30

Memory

30/30

qwen3.5:0.8b

Speed

40/40

TTFT

30/30

Memory

29/30

Quality

qwen3:0.6b

Reasoning

14/20

Coding

3/20

Instruction

11/20

Structured

13/15

Math

13/15

Multilingual

8/10

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

qwen3.5:0.8b

Reasoning

9/20

Coding

6/20

Instruction

11/20

Structured

13/15

Math

5/15

Multilingual

7/10

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

View qwen3:0.6b details | View qwen3.5:0.8b details

Run yours and compare

npx metrillm@latest bench

Requires Node 20+ and Ollama or LM Studio running