granite3.1-dense:2b
granite · 2.5B · Q4_K_M
Mar 2, 2026 · Apple M4
smollm2:360m
llama · 361.82M · F16
Mar 2, 2026 · Apple M4
Global Score
68 vs 52
Hardware Fit
100 vs 100
Quality Score
54 vs 32
Hardware
granite3.1-dense:2b smollm2:360m
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 smollm2:360m
Tokens/sec54.6117.9
TTFT121 ms43 ms
Load time0.4 s0.4 s
Memory usage5.6 GB1.2 GB
Memory %18%4%
HW Fit Score Breakdown
granite3.1-dense:2b
Speed
40/40
TTFT
30/30
Memory
30/30
smollm2:360m
Speed
40/40
TTFT
30/30
Memory
30/30
Quality
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
smollm2:360m
Reasoning
4/20
Coding
2/20
Instruction
10/20
Structured
9/15
Math
4/15
Multilingual
3/10
Reasoning: Poor Coding: Poor Instruction Following: Adequate Structured Output: Adequate Math: Poor Multilingual: Weak
Run yours and compare
npx metrillm@latest benchRequires Node 20+ and Ollama or LM Studio running