GPT-20B:20b
OLLAMA GGUFgptoss · 20.9B · MXFP4
Aug 19, 2026 · AMD Ryzen 9 9955HX3D 16-Core Processor
Kimi-48B:48B
OLLAMA GGUFkimi-linear · 49.1B · unknown
Aug 19, 2026 · Intel Core™ Ultra X7 358H
Global Score
90 vs 86
Hardware Fit
79 vs 78
Quality Score
94 vs 89
Hardware
GPT-20B:20b Kimi-48B:48B
MachineHP HyperX OMEN Gaming Laptop 16-ap1xxxGMKtec NucBox EVO-T2S
CPUAMD Ryzen 9 9955HX3D 16-Core ProcessorIntel Core™ Ultra X7 358H
Cores3216
RAM31 GB64 GB
GPUAMD Radeon(TM) 610M, NVIDIA GeForce RTX 5070 Laptop GPUIntel(R) Arc(TM) B390 GPU
OSMicrosoft Windows 11 Home 10.0.26200Microsoft Windows 11 Pro 10.0.26200
Archx64x64
Power Modebalancedbalanced
Performance
GPT-20B:20b Kimi-48B:48B
Tokens/sec36.622.8
First chunk722 ms721 ms
TTFT4.7 s721 ms
Load time0.3 s23.0 s
Memory usage13.1 GB25.5 GB
Memory %42%40%
HW Fit Score Breakdown
GPT-20B:20b
Speed
46/50
TTFT
6/20
Memory
27/30
Kimi-48B:48B
Speed
31/50
TTFT
20/20
Memory
27/30
Quality
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
Kimi-48B:48B
Reasoning
18/20
Coding
19/20
Instruction
15/20
Structured
15/15
Math
13/15
Multilingual
9/10
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