granite3.1-dense:2b

granite · 2.5B · Q4_K_M

Good

Mar 1, 2026 · Apple M4

starcoder2:7b

starcoder2 · 7B · Q4_0

Marginal

Mar 2, 2026 · Apple M4

Global Score

67 vs 44

Hardware Fit

99 vs 97

Quality Score

45 vs 8

Hardware

granite3.1-dense:2b starcoder2:7b

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 starcoder2:7b

Tokens/sec53.423.8

TTFT122 ms251 ms

Load time0.4 s0.4 s

Memory usage5.6 GB6.3 GB

Memory %18%20%

HW Fit Score Breakdown

granite3.1-dense:2b

Speed

40/40

TTFT

30/30

Memory

29/30

starcoder2:7b

Speed

37/40

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

starcoder2:7b

Reasoning

0/20

Coding

1/20

Instruction

4/20

Structured

2/15

Math

0/15

Multilingual

1/10

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

View granite3.1-dense:2b details | View starcoder2:7b details

Run yours and compare

npx metrillm@latest bench

Requires Node 20+ and Ollama or LM Studio running