GPT-20B:20b
OLLAMA GGUFgptoss · 20.9B · MXFP4
Aug 19, 2026 · AMD Ryzen 9 9955HX3D 16-Core Processor
GPT-120B:120b
OLLAMA GGUFgptoss · 116.8B · MXFP4
Aug 22, 2026 · NVIDIA RTX Spark N1X (6144-core GPU, 20-core ) RTX Spark N1X (6144-core GPU, 20-core )
Global Score
90 vs 66
Hardware Fit
79 vs 23
Quality Score
94 vs 84
Hardware
GPT-20B:20b GPT-120B:120b
MachineHP HyperX OMEN Gaming Laptop 16-ap1xxxHP HyperX OMEN Transcend Gaming Laptop 14-ga0xxx5CD612DXML
CPUAMD Ryzen 9 9955HX3D 16-Core ProcessorNVIDIA RTX Spark N1X (6144-core GPU, 20-core ) RTX Spark N1X (6144-core GPU, 20-core )
Cores3220
RAM31 GB55 GB
GPUAMD Radeon(TM) 610M, NVIDIA GeForce RTX 5070 Laptop GPUNVIDIA RTX Spark N1X (6144-core Blackwell RTX GPU), NVIDIA NPU
OSMicrosoft Windows 11 Home 10.0.26200Microsoft Windows 11 Pro 10.0.28000
Archx64arm64
Power Modebalancedbalanced
Performance
GPT-20B:20b GPT-120B:120b
Tokens/sec36.616.8
First chunk722 ms11247 ms
TTFT4.7 s12.2 s
Load time0.3 s77.3 s
Memory usage13.1 GB61.6 GB
Memory %42%113%
HW Fit Score Breakdown
GPT-20B:20b
Speed
46/50
TTFT
6/20
Memory
27/30
GPT-120B:120b
Speed
21/50
TTFT
2/20
Memory
0/30
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
GPT-120B:120b
Reasoning
16/20
Coding
19/20
Instruction
11/20
Structured
13/15
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