yi-coder:9b
OLLAMA GGUFllama · 8.8B · Q4_0
Mar 6, 2026 · Apple M4
gemma2:2b
OLLAMA GGUFgemma2 · 2.6B · Q4_0
Mar 2, 2026 · Apple M4
Global Score
70 vs 77
Hardware Fit
89 vs 100
Quality Score
62 vs 67
Hardware
yi-coder:9b gemma2:2b
MachineMacBook AirMacBook Air
CPUApple M4Apple M4
Cores1010
RAM32 GB32 GB
GPUApple M4Apple M4
OSmacOS 26.3macOS 26.3
Archarm64arm64
Power Modebalancedbalanced
Performance
yi-coder:9b gemma2:2b
Tokens/sec19.455.1
First chunk287 msN/A
TTFT287 ms152 ms
Load time0.7 s0.6 s
Memory usage9.6 GB2.8 GB
Memory %30%9%
HW Fit Score Breakdown
yi-coder:9b
Speed
39/50
TTFT
20/20
Memory
30/30
gemma2:2b
Speed
40/50
TTFT
30/20
Memory
30/30
Quality
yi-coder:9b
Reasoning
12/20
Coding
16/20
Instruction
13/20
Structured
7/15
Math
7/15
Multilingual
7/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Weak Math: Weak Multilingual: Adequate
gemma2:2b
Reasoning
11/20
Coding
13/20
Instruction
14/20
Structured
15/15
Math
4/15
Multilingual
10/10
Reasoning: Adequate Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Poor Multilingual: Strong
Run yours and compare
$
npm install -g metrillm@latest$
metrillmRequires Node 20+ and Ollama or LM Studio running
Or run without installing: npx metrillm@latest