phi3:3.8b
OLLAMA GGUFphi3 · 3.8B · Q4_0
Mar 2, 2026 · Apple M4
gpt-oss:20b
OLLAMA GGUFgptoss · 20.9B · MXFP4
Aug 18, 2026 · Intel Core™ Ultra X7 358H
Global Score
64 vs 81
Hardware Fit
100 vs 59
Quality Score
48 vs 91
Hardware
phi3:3.8b gpt-oss:20b
MachineMacBook AirGMKtec NucBox EVO-T2S
CPUApple M4Intel Core™ Ultra X7 358H
Cores1016
RAM32 GB64 GB
GPUApple M4Intel(R) Arc(TM) B390 GPU
OSmacOS 26.3Microsoft Windows 11 Pro 10.0.26200
Archarm64x64
Power Modebalancedbalanced
Performance
phi3:3.8b gpt-oss:20b
Tokens/sec42.019.1
First chunkN/A1985 ms
TTFT142 ms11.1 s
Load time1.1 s7.7 s
Memory usage16.0 GB12.9 GB
Memory %50%20%
HW Fit Score Breakdown
phi3:3.8b
Speed
40/50
TTFT
30/20
Memory
30/30
gpt-oss:20b
Speed
26/50
TTFT
3/20
Memory
30/30
Quality
phi3:3.8b
Reasoning
12/20
Coding
3/20
Instruction
11/20
Structured
10/15
Math
5/15
Multilingual
7/10
Reasoning: Adequate Coding: Poor Instruction Following: Adequate Structured Output: Adequate Math: Weak Multilingual: Adequate
gpt-oss:20b
Reasoning
18/20
Coding
19/20
Instruction
14/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Strong 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