Back to leaderboard

gemma2:2b

gemma2 · 2.6B · Q4_0

Good

Mar 1, 2026 · Apple M4

llama3:latest

llama · 8.0B · Q4_0

Good

Mar 2, 2026 · Apple M4

Global Score
72 vs 74
Hardware Fit
99 vs 95
Quality Score
54 vs 60

Hardware

gemma2:2b llama3:latest
MachineMacBook AirMacBook Air
CPUApple M4Apple M4
Cores1010
RAM32 GB32 GB
GPUApple M4Apple M4
OSmacOS 26.3macOS 26.3
Archarm64arm64
Power Modebalancedbalanced

Performance

gemma2:2b llama3:latest
Tokens/sec53.822.3
TTFT170 ms295 ms
Load time0.6 s0.8 s
Memory usage2.8 GB5.6 GB
Memory %9%18%

HW Fit Score Breakdown

gemma2:2b

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

llama3:latest

Speed
35/40
TTFT
30/30
Memory
30/30

Quality

gemma2:2b

Reasoning
11/20
Coding
0/20
Instruction
14/20
Structured
15/15
Math
4/15
Multilingual
10/10
Reasoning: Adequate Coding: Poor Instruction Following: Adequate Structured Output: Strong Math: Poor Multilingual: Strong

llama3:latest

Reasoning
9/20
Coding
9/20
Instruction
15/20
Structured
13/15
Math
4/15
Multilingual
10/10
Reasoning: Weak Coding: Weak Instruction Following: Strong Structured Output: Strong Math: Weak Multilingual: Strong
View gemma2:2b details | View llama3:latest details

Run yours and compare

npx metrillm@latest bench

Requires Node 20+ and Ollama or LM Studio running