orca-mini:3b
OLLAMA GGUFllama · 3B · Q4_0
Mar 1, 2026 · Apple M4
gemma3n:latest
OLLAMA GGUFgemma3n · 6.9B · Q4_K_M
Mar 6, 2026 · AMD EPYC 9654P 96-Core Processor
Global Score
47 vs 81
Hardware Fit
100 vs 100
Quality Score
24 vs 73
Hardware
orca-mini:3b 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
orca-mini:3b gemma3n:latest
Tokens/sec30.6108.7
First chunkN/A333 ms
TTFT126 ms333 ms
Load time0.4 s4.5 s
Memory usage2.6 GB8.6 GB
Memory %8%7%
HW Fit Score Breakdown
orca-mini:3b
Speed
40/50
TTFT
30/20
Memory
30/30
gemma3n:latest
Speed
50/50
TTFT
20/20
Memory
30/30
Quality
orca-mini:3b
Reasoning
2/20
Coding
2/20
Instruction
13/20
Structured
3/15
Math
1/15
Multilingual
3/10
Reasoning: Poor Coding: Poor Instruction Following: Adequate Structured Output: Poor Math: Poor Multilingual: Weak
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