qwen3.5:27b

qwen35 · 27.8B · Q4_K_M

Good

Mar 3, 2026 · Apple M4

granite3.1-dense:2b

granite · 2.5B · Q4_K_M

Good

Mar 2, 2026 · Apple M4

Global Score

75 vs 68

Hardware Fit

67 vs 100

Quality Score

79 vs 54

Hardware

qwen3.5:27b granite3.1-dense:2b

MachineMacBook AirMacBook Air

CPUApple M4Apple M4

Cores1010

RAM32 GB32 GB

GPUApple M4Apple M4

OSmacOS 26.3macOS 26.3

Archarm64arm64

Power Modebalancedbalanced

Performance

qwen3.5:27b granite3.1-dense:2b

Tokens/sec4.454.6

TTFT1.1 s121 ms

Load time13.2 s0.4 s

Memory usage22.7 GB5.6 GB

Memory %71%18%

HW Fit Score Breakdown

qwen3.5:27b

Speed

7/40

TTFT

30/30

Memory

30/30

granite3.1-dense:2b

Speed

40/40

TTFT

30/30

Memory

30/30

Quality

qwen3.5:27b

Reasoning

16/20

Coding

17/20

Instruction

9/20

Structured

15/15

Math

12/15

Multilingual

10/10

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

granite3.1-dense:2b

Reasoning

8/20

Coding

9/20

Instruction

13/20

Structured

14/15

Math

3/15

Multilingual

7/10

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

View qwen3.5:27b details | View granite3.1-dense:2b details

Run yours and compare

npx metrillm@latest bench

Requires Node 20+ and Ollama or LM Studio running