granite3.1-dense:2b

granite · 2.5B · Q4_K_M

Good

Mar 1, 2026 · Apple M4

codegemma:7b

gemma · 9B · Q4_0

Good

Mar 1, 2026 · Apple M4

Global Score

67 vs 65

Hardware Fit

99 vs 91

Quality Score

45 vs 48

Hardware

granite3.1-dense:2b codegemma:7b

MachineMacBook AirMacBook Air

CPUApple M4Apple M4

Cores1010

RAM32 GB32 GB

GPUApple M4Apple M4

OSmacOS 26.3macOS 26.3

Archarm64arm64

Power Modebalancedbalanced

Performance

granite3.1-dense:2b codegemma:7b

Tokens/sec53.419.2

TTFT122 ms316 ms

Load time0.4 s0.1 s

Memory usage5.6 GB8.7 GB

Memory %18%27%

HW Fit Score Breakdown

granite3.1-dense:2b

Speed

40/40

TTFT

30/30

Memory

29/30

codegemma:7b

Speed

31/40

TTFT

30/30

Memory

30/30

Quality

granite3.1-dense:2b

Reasoning

8/20

Coding

0/20

Instruction

13/20

Structured

14/15

Math

3/15

Multilingual

7/10

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

codegemma:7b

Reasoning

1/20

Coding

0/20

Instruction

13/20

Structured

15/15

Math

10/15

Multilingual

9/10

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

View granite3.1-dense:2b details | View codegemma:7b details

Run yours and compare

npx metrillm@latest bench

Requires Node 20+ and Ollama or LM Studio running