qwen2.5:0.5b

qwen2 · 494.03M · 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

63 vs 70

Hardware Fit

100 vs 99

Quality Score

39 vs 51

Hardware

qwen2.5:0.5b 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

qwen2.5:0.5b qwen3.5:0.8b

Tokens/sec165.048.2

TTFT81 ms195 ms

Load time0.5 s1.0 s

Memory usage1.7 GB2.5 GB

Memory %5%8%

HW Fit Score Breakdown

qwen2.5:0.5b

Speed

40/40

TTFT

30/30

Memory

30/30

qwen3.5:0.8b

Speed

40/40

TTFT

30/30

Memory

29/30

Quality

qwen2.5:0.5b

Reasoning

6/20

Coding

6/20

Instruction

7/20

Structured

11/15

Math

5/15

Multilingual

4/10

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

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 qwen2.5:0.5b details | View qwen3.5:0.8b details

Run yours and compare

npx metrillm@latest bench

Requires Node 20+ and Ollama or LM Studio running