phi4-mini
OLLAMA GGUFAug 28, 2026 · Intel Core™ i5-10210U
GPT-20B:20b
OLLAMA GGUFgptoss · 20.9B · MXFP4
Aug 19, 2026 · Intel Core™ Ultra X7 358H
Global Score
51 vs 79
Hardware Fit
46 vs 59
Quality Score
53 vs 88
Hardware
phi4-mini GPT-20B:20b
MachineLENOVO 20U30029MBGMKtec NucBox EVO-T2S
CPUIntel Core™ i5-10210UIntel Core™ Ultra X7 358H
Cores816
RAM15 GB64 GB
GPUCometLake-U GT2 [UHD Graphics]Intel(R) Arc(TM) B390 GPU
OSPop 24.04 LTSMicrosoft Windows 11 Pro 10.0.26200
Archx64x64
Power Modeperformancebalanced
Performance
phi4-mini GPT-20B:20b
Tokens/sec2.619.3
First chunk5406 ms2004 ms
TTFT5.4 s10.4 s
Load time27.4 s10.4 s
Memory usage4.6 GB12.9 GB
Memory %30%20%
HW Fit Score Breakdown
phi4-mini
Speed
6/50
TTFT
10/20
Memory
30/30
GPT-20B:20b
Speed
26/50
TTFT
3/20
Memory
30/30
Quality
phi4-mini
Reasoning
11/20
Coding
9/20
Instruction
6/20
Structured
12/15
Math
5/15
Multilingual
10/10
Reasoning: Adequate Coding: Weak Instruction Following: Weak Structured Output: Strong Math: Weak Multilingual: Strong
GPT-20B:20b
Reasoning
19/20
Coding
18/20
Instruction
11/20
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