phi4-mini:latest
OLLAMA GGUFphi3 · 3.8B · Q4_K_M
Nov 4, 2026 · Intel Core™ i7-9700
GPT-20B:20b
OLLAMA GGUFgptoss · 20.9B · MXFP4
Aug 19, 2026 · AMD Ryzen 9 9955HX3D 16-Core Processor
Global Score
75 vs 87
Hardware Fit
84 vs 81
Quality Score
71 vs 90
Hardware
phi4-mini:latest GPT-20B:20b
MachineVMware, Inc. VMware Virtual PlatformHP HyperX OMEN Gaming Laptop 16-ap1xxx
CPUIntel Core™ i7-9700AMD Ryzen 9 9955HX3D 16-Core Processor
Cores432
RAM16 GB31 GB
GPUIntegrated / UnknownAMD Radeon(TM) 610M, NVIDIA GeForce RTX 5070 Laptop GPU
OSUbuntu 24.04.5 LTSMicrosoft Windows 11 Home 10.0.26200
Archx64x64
Power Modeunknownbalanced
Performance
phi4-mini:latest GPT-20B:20b
Tokens/sec10.836.9
First chunk643 ms902 ms
TTFT643 ms4.2 s
Load time31.5 s19.5 s
Memory usage2.9 GB13.1 GB
Memory %19%42%
HW Fit Score Breakdown
phi4-mini:latest
Speed
34/50
TTFT
20/20
Memory
30/30
GPT-20B:20b
Speed
47/50
TTFT
7/20
Memory
27/30
Quality
phi4-mini:latest
Reasoning
13/20
Coding
14/20
Instruction
15/20
Structured
14/15
Math
6/15
Multilingual
9/10
Reasoning: Adequate Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Weak Multilingual: Strong
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