qwen3:8b
OLLAMA GGUFqwen3 · 8.2B · Q4_K_M
Mar 5, 2026 · Intel Core™ Ultra 9 285K
GPT-20B:20b
OLLAMA GGUFgptoss · 20.9B · MXFP4
Aug 24, 2026 · Intel Core™ Ultra X7 358H
Global Score
84 vs 78
Hardware Fit
97 vs 59
Quality Score
79 vs 86
Hardware
qwen3:8b GPT-20B:20b
MachineASUSGMKtec NucBox EVO-T2S
CPUIntel Core™ Ultra 9 285KIntel Core™ Ultra X7 358H
Cores2416
RAM47 GB64 GB
GPUNVIDIA GeForce RTX 5090, Intel(R) GraphicsIntel(R) Arc(TM) B390 GPU
OSMicrosoft Windows 11 Pro 10.0.26200Microsoft Windows 11 Pro 10.0.26200
Archx64x64
Power Modebalancedbalanced
Performance
qwen3:8b GPT-20B:20b
Tokens/sec208.019.6
First chunk82 ms2068 ms
TTFT1.3 s9.9 s
Load time1.5 s12.8 s
Memory usage9.6 GB12.9 GB
Memory %20%20%
HW Fit Score Breakdown
qwen3:8b
Speed
50/50
TTFT
18/20
Memory
29/30
GPT-20B:20b
Speed
26/50
TTFT
3/20
Memory
30/30
Quality
qwen3:8b
Reasoning
18/20
Coding
10/20
Instruction
14/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong
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
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