GPT-120B:120b
OLLAMA GGUFgptoss · 116.8B · MXFP4
Aug 18, 2026 · Intel Core™ i7-14700F
Kimi-48B:48B
OLLAMA GGUFkimi-linear · 49.1B · unknown
Aug 19, 2026 · Intel Core™ i7-14700F
Global Score
79 vs 85
Hardware Fit
47 vs 83
Quality Score
93 vs 86
Hardware
GPT-120B:120b Kimi-48B:48B
MachineHP OMEN 35L VALORANT Limited Edition Gaming Desktop PCHP OMEN 35L VALORANT Limited Edition Gaming Desktop PC
CPUIntel Core™ i7-14700FIntel Core™ i7-14700F
Cores2828
RAM128 GB64 GB
GPUNVIDIA GeForce RTX 5080NVIDIA GeForce RTX 5080
OSMicrosoft Windows 11 Enterprise 10.0.26200Microsoft Windows 11 Enterprise 10.0.26200
Archx64x64
Power Modebalancedbalanced
Performance
GPT-120B:120b Kimi-48B:48B
Tokens/sec18.232.8
First chunk1719 ms724 ms
TTFT3.9 s724 ms
Load time50.9 s20.9 s
Memory usage61.5 GB25.8 GB
Memory %48%41%
HW Fit Score Breakdown
GPT-120B:120b
Speed
17/50
TTFT
5/20
Memory
25/30
Kimi-48B:48B
Speed
36/50
TTFT
20/20
Memory
27/30
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
Kimi-48B:48B
Reasoning
16/20
Coding
17/20
Instruction
15/20
Structured
15/15
Math
13/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong 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