qwen3.5:0.8b

qwen35 · 873.44M · Q8_0

Good

Mar 2, 2026 · Apple M4

phi3:14b

phi3 · 14.0B · Q4_0

Good

Mar 2, 2026 · Apple M4

Global Score

65 vs 63

Hardware Fit

99 vs 83

Quality Score

51 vs 55

Hardware

qwen3.5:0.8b phi3:14b

MachineMacBook AirMacBook Air

CPUApple M4Apple M4

Cores1010

RAM32 GB32 GB

GPUApple M4Apple M4

OSmacOS 26.3macOS 26.3

Archarm64arm64

Power Modebalancedbalanced

Performance

qwen3.5:0.8b phi3:14b

Tokens/sec48.212.7

TTFT195 ms434 ms

Load time1.0 s0.9 s

Memory usage2.5 GB17.7 GB

Memory %8%55%

HW Fit Score Breakdown

qwen3.5:0.8b

Speed

40/40

TTFT

30/30

Memory

29/30

phi3:14b

Speed

23/40

TTFT

30/30

Memory

30/30

Quality

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

phi3:14b

Reasoning

14/20

Coding

2/20

Instruction

14/20

Structured

7/15

Math

8/15

Multilingual

10/10

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

View qwen3.5:0.8b details | View phi3:14b details

Run yours and compare

npx metrillm@latest bench

Requires Node 20+ and Ollama or LM Studio running