qwen3.5:0.8b

qwen35 · 873.44M · Q8_0

Good

Mar 2, 2026 · Apple M4

qwen3:0.6b

qwen3 · 751.63M · Q4_K_M

Good

Mar 2, 2026 · Apple M4

Global Score

65 vs 61

Hardware Fit

99 vs 100

Quality Score

51 vs 44

Hardware

qwen3.5:0.8b qwen3:0.6b

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 qwen3:0.6b

Tokens/sec48.2144.3

TTFT195 ms81 ms

Load time1.0 s0.9 s

Memory usage2.5 GB4.1 GB

Memory %8%13%

HW Fit Score Breakdown

qwen3.5:0.8b

Speed

40/40

TTFT

30/30

Memory

29/30

qwen3:0.6b

Speed

40/40

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

qwen3:0.6b

Reasoning

6/20

Coding

4/20

Instruction

10/20

Structured

13/15

Math

6/15

Multilingual

5/10

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

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

Run yours and compare

npx metrillm@latest bench

Requires Node 20+ and Ollama or LM Studio running