phi4-mini:latest
OLLAMA GGUFphi3 · 3.8B · Q4_K_M
Jun 26, 2026 · Cortex-A78AE
GPT-20B:20b
OLLAMA GGUFgptoss · 20.9B · MXFP4
Aug 19, 2026 · AMD Ryzen 9 9955HX3D 16-Core Processor
Global Score
74 vs 90
Hardware Fit
98 vs 79
Quality Score
63 vs 94
Hardware
phi4-mini:latest GPT-20B:20b
MachineNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit SuperHP HyperX OMEN Gaming Laptop 16-ap1xxx
CPUCortex-A78AEAMD Ryzen 9 9955HX3D 16-Core Processor
Cores632
RAM7 GB31 GB
GPUIntegrated / UnknownAMD Radeon(TM) 610M, NVIDIA GeForce RTX 5070 Laptop GPU
OSUbuntu 22.04.5 LTSMicrosoft Windows 11 Home 10.0.26200
Archarm64x64
Power Modebalancedbalanced
Performance
phi4-mini:latest GPT-20B:20b
Tokens/sec18.436.6
First chunk1078 ms722 ms
TTFT1.1 s4.7 s
Load time6.4 s0.3 s
Memory usage2.9 GB13.1 GB
Memory %39%42%
HW Fit Score Breakdown
phi4-mini:latest
Speed
50/50
TTFT
20/20
Memory
28/30
GPT-20B:20b
Speed
46/50
TTFT
6/20
Memory
27/30
Quality
phi4-mini:latest
Reasoning
13/20
Coding
11/20
Instruction
14/20
Structured
11/15
Math
5/15
Multilingual
9/10
Reasoning: Adequate Coding: Adequate Instruction Following: Adequate Structured Output: Adequate Math: Weak Multilingual: Strong
GPT-20B:20b
Reasoning
19/20
Coding
18/20
Instruction
17/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong 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