GPT-120B:120b
OLLAMA GGUFgptoss · 116.8B · MXFP4
Aug 18, 2026 · Intel Core™ i7-14700F
qwen3.5:4b
OLLAMA GGUFqwen35 · 4.2B · Q4_K_M
Oct 12, 2026 · AMD Ryzen 5 5500
Global Score
79 vs 81
Hardware Fit
47 vs 98
Quality Score
93 vs 74
Hardware
GPT-120B:120b qwen3.5:4b
MachineHP OMEN 35L VALORANT Limited Edition Gaming Desktop PCMicrosoft WSL
CPUIntel Core™ i7-14700FAMD Ryzen 5 5500
Cores2812
RAM128 GB8 GB
GPUNVIDIA GeForce RTX 5080Integrated / Unknown
OSMicrosoft Windows 11 Enterprise 10.0.26200Ubuntu 26.04.1 LTS
Archx64x64
Power Modebalancedunknown
Performance
GPT-120B:120b qwen3.5:4b
Tokens/sec18.293.7
First chunk1719 ms249 ms
TTFT3.9 s249 ms
Load time50.9 s10.1 s
Memory usage61.5 GB2.9 GB
Memory %48%38%
HW Fit Score Breakdown
GPT-120B:120b
Speed
17/50
TTFT
5/20
Memory
25/30
qwen3.5:4b
Speed
50/50
TTFT
20/20
Memory
28/30
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
qwen3.5:4b
Reasoning
15/20
Coding
13/20
Instruction
15/20
Structured
15/15
Math
7/15
Multilingual
9/10
Reasoning: Strong Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Weak 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