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 )
qwen3.5:9b
OLLAMA GGUFqwen35 · 9.7B · Q4_K_M
Mar 7, 2026 · AMD Ryzen 5 5500
Global Score
66 vs 71
Hardware Fit
23 vs 56
Quality Score
84 vs 78
Hardware
GPT-120B:120b qwen3.5:9b
MachineHP HyperX OMEN Transcend Gaming Laptop 14-ga0xxx5CD612DXMLSystem manufacturer
CPUNVIDIA RTX Spark N1X (6144-core GPU, 20-core ) RTX Spark N1X (6144-core GPU, 20-core )AMD Ryzen 5 5500
Cores2012
RAM55 GB16 GB
GPUNVIDIA RTX Spark N1X (6144-core Blackwell RTX GPU), NVIDIA NPUNVIDIA GeForce RTX 3060
OSMicrosoft Windows 11 Pro 10.0.28000Microsoft Windows 11 IoT Enterprise LTSC 10.0.26100
Archarm64x64
Power Modebalancedbalanced
Performance
GPT-120B:120b qwen3.5:9b
Tokens/sec16.85.3
First chunk11247 ms1624 ms
TTFT12.2 s1.6 s
Load time77.3 s4.0 s
Memory usage61.6 GB7.9 GB
Memory %113%50%
HW Fit Score Breakdown
GPT-120B:120b
Speed
21/50
TTFT
2/20
Memory
0/30
qwen3.5:9b
Speed
11/50
TTFT
20/20
Memory
25/30
Quality
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
qwen3.5:9b
Reasoning
14/20
Coding
17/20
Instruction
12/20
Structured
15/15
Math
10/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Adequate 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