Back to leaderboard

granite3.1-dense:2b

granite · 2.5B · Q4_K_M

Good

Mar 1, 2026 · Apple M4

aya:8b

command-r · 8.0B · F16

Good

Mar 1, 2026 · Apple M4

Global Score
67 vs 70
Hardware Fit
99 vs 92
Quality Score
45 vs 55

Hardware

granite3.1-dense:2b aya:8b
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 aya:8b
Tokens/sec53.420.0
TTFT122 ms300 ms
Load time0.4 s0.9 s
Memory usage5.6 GB6.0 GB
Memory %18%19%

HW Fit Score Breakdown

granite3.1-dense:2b

Speed
40/40
TTFT
30/30
Memory
29/30

aya:8b

Speed
32/40
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

aya:8b

Reasoning
10/20
Coding
6/20
Instruction
13/20
Structured
15/15
Math
2/15
Multilingual
9/10
Reasoning: Adequate Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Poor Multilingual: Strong
View granite3.1-dense:2b details | View aya:8b details

Run yours and compare

npx metrillm@latest bench

Requires Node 20+ and Ollama or LM Studio running