phi-1_5
LM-STUDIO GGUFphi2 · Q8_0
Mar 6, 2026 · Intel Core™ i5-5300U
GPT-20B:20b
OLLAMA GGUFgptoss · 20.9B · MXFP4
Aug 24, 2026 · Intel Core™ Ultra X7 358H
Global Score
28 vs 78
Hardware Fit
66 vs 59
Quality Score
11 vs 86
Hardware
phi-1_5 GPT-20B:20b
MachineLENOVO 20BUS00700GMKtec NucBox EVO-T2S
CPUIntel Core™ i5-5300UIntel Core™ Ultra X7 358H
Cores416
RAM16 GB64 GB
GPUIntel(R) HD Graphics 5500Intel(R) Arc(TM) B390 GPU
OSMicrosoft Windows 10 Professionnel 10.0.19045Microsoft Windows 11 Pro 10.0.26200
Archx64x64
Power Modebalancedbalanced
Performance
phi-1_5 GPT-20B:20b
Tokens/sec6.919.6
First chunk3040 ms2068 ms
TTFT3.0 s9.9 s
Load timeN/A12.8 s
Memory usage1.4 GB12.9 GB
Memory %9%20%
HW Fit Score Breakdown
phi-1_5
Speed
24/50
TTFT
16/20
Memory
26/30
GPT-20B:20b
Speed
26/50
TTFT
3/20
Memory
30/30
Quality
phi-1_5
Reasoning
2/20
Coding
2/20
Instruction
3/20
Structured
0/15
Math
2/15
Multilingual
2/10
Reasoning: Poor Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Poor Multilingual: Poor
GPT-20B:20b
Reasoning
18/20
Coding
18/20
Instruction
11/20
Structured
14/15
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