Qwen3-30B:30b
OLLAMA GGUFqwen3moe · 30.5B · Q4_K_M
Aug 22, 2026 · NVIDIA RTX Spark N1X (6144-core GPU, 20-core ) RTX Spark N1X (6144-core GPU, 20-core )
GPT-120B:120b
OLLAMA GGUFgptoss · 116.8B · MXFP4
Aug 25, 2026 · Intel Core™ Ultra X7 358H
Global Score
91 vs 68
Hardware Fit
98 vs 21
Quality Score
88 vs 88
Hardware
Qwen3-30B:30b GPT-120B:120b
MachineHP HyperX OMEN Transcend Gaming Laptop 14-ga0xxx5CD612DXMLGMKtec NucBox EVO-T2S
CPUNVIDIA RTX Spark N1X (6144-core GPU, 20-core ) RTX Spark N1X (6144-core GPU, 20-core )Intel Core™ Ultra X7 358H
Cores2016
RAM55 GB64 GB
GPUNVIDIA RTX Spark N1X (6144-core Blackwell RTX GPU), NVIDIA NPUIntel(R) Arc(TM) B390 GPU
OSMicrosoft Windows 11 Pro 10.0.28000Microsoft Windows 11 Pro 10.0.26200
Archarm64x64
Power Modebalancedbalanced
Performance
Qwen3-30B:30b GPT-120B:120b
Tokens/sec80.512.1
First chunk158 ms4392 ms
TTFT158 ms8.7 s
Load time21.8 s80.1 s
Memory usage20.3 GB61.0 GB
Memory %37%96%
HW Fit Score Breakdown
Qwen3-30B:30b
Speed
50/50
TTFT
20/20
Memory
28/30
GPT-120B:120b
Speed
15/50
TTFT
4/20
Memory
2/30
Quality
Qwen3-30B:30b
Reasoning
16/20
Coding
19/20
Instruction
17/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong
GPT-120B:120b
Reasoning
18/20
Coding
19/20
Instruction
11/20
Structured
15/15
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