GPT-120B:120b
OLLAMA GGUFgptoss · 116.8B · MXFP4
Aug 18, 2026 · Intel Core™ i7-14700F
qwen3.5:4b
OLLAMA GGUFqwen35 · 4.7B · Q4_K_M
Mar 5, 2026 · Intel Core™ i5-6500
Global Score
79 vs 61
Hardware Fit
47 vs 69
Quality Score
93 vs 58
Hardware
GPT-120B:120b qwen3.5:4b
MachineHP OMEN 35L VALORANT Limited Edition Gaming Desktop PCGigabyte Technology Co., Ltd. H170M-D3H
CPUIntel Core™ i7-14700FIntel Core™ i5-6500
Cores284
RAM128 GB16 GB
GPUNVIDIA GeForce RTX 5080GP104 [GeForce GTX 1070]
OSMicrosoft Windows 11 Enterprise 10.0.26200Ubuntu 24.04.4 LTS
Archx64x64
Power Modebalancedlow-power
Performance
GPT-120B:120b qwen3.5:4b
Tokens/sec18.235.7
First chunk1719 ms438 ms
TTFT3.9 s5.1 s
Load time50.9 s40.1 s
Memory usage61.5 GB5.5 GB
Memory %48%35%
HW Fit Score Breakdown
GPT-120B:120b
Speed
17/50
TTFT
5/20
Memory
25/30
qwen3.5:4b
Speed
50/50
TTFT
11/20
Memory
8/30
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
18/20
Coding
1/20
Instruction
8/20
Structured
8/15
Math
13/15
Multilingual
10/10
Reasoning: Strong Coding: Poor Instruction Following: Weak 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