llama2:13b
OLLAMA GGUFllama · 13B · Q4_0
Mar 2, 2026 · Apple M4
gemma3n:latest
OLLAMA GGUFgemma3n · 6.9B · Q4_K_M
Mar 6, 2026 · AMD EPYC 9654P 96-Core Processor
Global Score
56 vs 81
Hardware Fit
84 vs 100
Quality Score
44 vs 73
Hardware
llama2:13b gemma3n:latest
MachineMacBook AirSupermicro AS -2015HS-TNR
CPUApple M4AMD EPYC 9654P 96-Core Processor
Cores1064
RAM32 GB128 GB
GPUApple M4GH100 [H100L 94GB], ASPEED Graphics Family, GH100 [H100L 94GB]
OSmacOS 26.3Ubuntu 24.04.3 LTS
Archarm64x64
Power Modebalancedperformance
Performance
llama2:13b gemma3n:latest
Tokens/sec13.5108.7
First chunkN/A333 ms
TTFT415 ms333 ms
Load time0.6 s4.5 s
Memory usage10.3 GB8.6 GB
Memory %32%7%
HW Fit Score Breakdown
llama2:13b
Speed
24/50
TTFT
30/20
Memory
30/30
gemma3n:latest
Speed
50/50
TTFT
20/20
Memory
30/30
Quality
llama2:13b
Reasoning
9/20
Coding
3/20
Instruction
13/20
Structured
7/15
Math
3/15
Multilingual
9/10
Reasoning: Weak Coding: Poor Instruction Following: Adequate Structured Output: Weak Math: Poor Multilingual: Strong
gemma3n:latest
Reasoning
14/20
Coding
14/20
Instruction
14/20
Structured
14/15
Math
7/15
Multilingual
10/10
Reasoning: Adequate Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Weak 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