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-coder:30b
OLLAMA GGUFqwen3moe · 30.5B · Q4_K_M
Mar 4, 2026 · Intel Gen Intel® Core™ i7-12700K
Global Score
66 vs 80
Hardware Fit
23 vs 60
Quality Score
84 vs 88
Hardware
GPT-120B:120b qwen3-coder:30b
MachineHP HyperX OMEN Transcend Gaming Laptop 14-ga0xxx5CD612DXMLASUS
CPUNVIDIA RTX Spark N1X (6144-core GPU, 20-core ) RTX Spark N1X (6144-core GPU, 20-core )Intel Gen Intel® Core™ i7-12700K
Cores2020
RAM55 GB96 GB
GPUNVIDIA RTX Spark N1X (6144-core Blackwell RTX GPU), NVIDIA NPUParsec Virtual Display Adapter, NVIDIA GeForce RTX 2060
OSMicrosoft Windows 11 Pro 10.0.28000Microsoft Windows 11 Enterprise 10.0.26200
Archarm64x64
Power Modebalancedbalanced
Performance
GPT-120B:120b qwen3-coder:30b
Tokens/sec16.814.7
First chunk11247 ms796 ms
TTFT12.2 s796 ms
Load time77.3 s0.2 s
Memory usage61.6 GB17.9 GB
Memory %113%19%
HW Fit Score Breakdown
GPT-120B:120b
Speed
21/50
TTFT
2/20
Memory
0/30
qwen3-coder:30b
Speed
14/50
TTFT
19/20
Memory
27/30
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-coder:30b
Reasoning
17/20
Coding
19/20
Instruction
16/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong 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