GPT-120B:120b
OLLAMA GGUFgptoss · 116.8B · MXFP4
Aug 18, 2026 · Intel Core™ i7-14700F
qwen3-vl:8b
OLLAMA GGUFqwen3vl · 8.8B · Q4_K_M
Apr 28, 2026 · Intel Xeon® Gold 6230
Global Score
79 vs 72
Hardware Fit
47 vs 89
Quality Score
93 vs 64
Hardware
GPT-120B:120b qwen3-vl:8b
MachineHP OMEN 35L VALORANT Limited Edition Gaming Desktop PCHP HP Z8 G4 Workstation
CPUIntel Core™ i7-14700FIntel Xeon® Gold 6230
Cores2880
RAM128 GB252 GB
GPUNVIDIA GeForce RTX 5080TU104GL [Quadro RTX 5000]
OSMicrosoft Windows 11 Enterprise 10.0.26200Ubuntu 24.04.4 LTS
Archx64x64
Power Modebalancedlow-power
Performance
GPT-120B:120b qwen3-vl:8b
Tokens/sec18.268.2
First chunk1719 ms285 ms
TTFT3.9 s2.0 s
Load time50.9 s42.4 s
Memory usage61.5 GB7.1 GB
Memory %48%3%
HW Fit Score Breakdown
GPT-120B:120b
Speed
17/50
TTFT
5/20
Memory
25/30
qwen3-vl:8b
Speed
50/50
TTFT
9/20
Memory
30/30
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-vl:8b
Reasoning
16/20
Coding
3/20
Instruction
10/20
Structured
11/15
Math
14/15
Multilingual
10/10
Reasoning: Strong Coding: Poor Instruction Following: Adequate Structured Output: Adequate 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