GPT-20B:20b
OLLAMA GGUFgptoss · 20.9B · MXFP4
Aug 24, 2026 · Intel Core™ Ultra X7 358H
Qwen3.8-27B-UD-Q3_K_XL
OLLAMA GGUFllama · 27.3B · Q4_K
Aug 23, 2026 · Intel Gen Intel® Core™ i5-12600K
Global Score
78 vs 90
Hardware Fit
59 vs 97
Quality Score
86 vs 87
Hardware
GPT-20B:20b Qwen3.8-27B-UD-Q3_…
MachineGMKtec NucBox EVO-T2S—
CPUIntel Core™ Ultra X7 358HIntel Gen Intel® Core™ i5-12600K
Cores1616
RAM64 GB31 GB
GPUIntel(R) Arc(TM) B390 GPUAlderLake-S GT1, AD106 [GeForce RTX 4060 Ti 16GB]
OSMicrosoft Windows 11 Pro 10.0.26200Ubuntu 24.04.4 LTS
Archx64x64
Power Modebalancedlow-power
Performance
GPT-20B:20b Qwen3.8-27B-UD-Q3_…
Tokens/sec19.639.0
First chunk2068 ms305 ms
TTFT9.9 s305 ms
Load time12.8 s0.0 s
Memory usage12.9 GB12.5 GB
Memory %20%41%
HW Fit Score Breakdown
GPT-20B:20b
Speed
26/50
TTFT
3/20
Memory
30/30
Qwen3.8-27B-UD-Q3_K_XL
Speed
50/50
TTFT
20/20
Memory
27/30
Quality
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
Qwen3.8-27B-UD-Q3_K_XL
Reasoning
17/20
Coding
19/20
Instruction
15/20
Structured
15/15
Math
11/15
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