phi-1_5
LM-STUDIO GGUFphi2 · Q8_0
Mar 6, 2026 · Intel Core™ i5-5300U
GPT-20B:20b
OLLAMA GGUFgptoss · 20.9B · MXFP4
Aug 19, 2026 · AMD Ryzen 9 9955HX3D 16-Core Processor
Global Score
28 vs 87
Hardware Fit
66 vs 81
Quality Score
11 vs 90
Hardware
phi-1_5 GPT-20B:20b
MachineLENOVO 20BUS00700HP HyperX OMEN Gaming Laptop 16-ap1xxx
CPUIntel Core™ i5-5300UAMD Ryzen 9 9955HX3D 16-Core Processor
Cores432
RAM16 GB31 GB
GPUIntel(R) HD Graphics 5500AMD Radeon(TM) 610M, NVIDIA GeForce RTX 5070 Laptop GPU
OSMicrosoft Windows 10 Professionnel 10.0.19045Microsoft Windows 11 Home 10.0.26200
Archx64x64
Power Modebalancedbalanced
Performance
phi-1_5 GPT-20B:20b
Tokens/sec6.936.9
First chunk3040 ms902 ms
TTFT3.0 s4.2 s
Load timeN/A19.5 s
Memory usage1.4 GB13.1 GB
Memory %9%42%
HW Fit Score Breakdown
phi-1_5
Speed
24/50
TTFT
16/20
Memory
26/30
GPT-20B:20b
Speed
47/50
TTFT
7/20
Memory
27/30
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
19/20
Coding
17/20
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