GPT-120B:120b
OLLAMA GGUFgptoss · 116.8B · MXFP4
Aug 18, 2026 · Intel Core™ i7-14700F
qwen3-coder:30b
OLLAMA GGUFqwen3moe · 30.5B · Q4_K_M
Mar 5, 2026 · Intel Core™ Ultra 9 285K
Global Score
79 vs 90
Hardware Fit
47 vs 96
Quality Score
93 vs 87
Hardware
GPT-120B:120b qwen3-coder:30b
MachineHP OMEN 35L VALORANT Limited Edition Gaming Desktop PCASUS
CPUIntel Core™ i7-14700FIntel Core™ Ultra 9 285K
Cores2824
RAM128 GB47 GB
GPUNVIDIA GeForce RTX 5080NVIDIA GeForce RTX 5090, Intel(R) Graphics
OSMicrosoft Windows 11 Enterprise 10.0.26200Microsoft Windows 11 Pro 10.0.26200
Archx64x64
Power Modebalancedbalanced
Performance
GPT-120B:120b qwen3-coder:30b
Tokens/sec18.2207.9
First chunk1719 ms513 ms
TTFT3.9 s513 ms
Load time50.9 s4.9 s
Memory usage61.5 GB20.5 GB
Memory %48%43%
HW Fit Score Breakdown
GPT-120B:120b
Speed
17/50
TTFT
5/20
Memory
25/30
qwen3-coder:30b
Speed
50/50
TTFT
20/20
Memory
26/30
Quality
GPT-120B:120b
Reasoning
19/20
Coding
19/20
Instruction
15/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
qwen3-coder:30b
Reasoning
16/20
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