GPT-120B:120b
OLLAMA GGUFgptoss · 116.8B · MXFP4
Aug 18, 2026 · Intel Core™ i7-14700F
gemma-4-26b-a4b-it-qat
LM-STUDIO GGUFgemma4 · 26B · Q4_K_XL
Jul 7, 2026 · AMD Ryzen 7 7800X3D 8-Core Processor
Global Score
79 vs 91
Hardware Fit
47 vs 86
Quality Score
93 vs 93
Hardware
GPT-120B:120b gemma-4-26b-a4b-it…
MachineHP OMEN 35L VALORANT Limited Edition Gaming Desktop PCASUS
CPUIntel Core™ i7-14700FAMD Ryzen 7 7800X3D 8-Core Processor
Cores2816
RAM128 GB31 GB
GPUNVIDIA GeForce RTX 5080NVIDIA GeForce RTX 4090, Raphael
OSMicrosoft Windows 11 Enterprise 10.0.26200cachyos rolling
Archx64x64
Power Modebalancedlow-power
Performance
GPT-120B:120b gemma-4-26b-a4b-it…
Tokens/sec18.2167.8
First chunk1719 ms18 ms
TTFT3.9 s128 ms
Load time50.9 sN/A
Memory usage61.5 GB20.9 GB
Memory %48%69%
HW Fit Score Breakdown
GPT-120B:120b
Speed
17/50
TTFT
5/20
Memory
25/30
gemma-4-26b-a4b-it-qat
Speed
50/50
TTFT
20/20
Memory
16/30
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
gemma-4-26b-a4b-it-qat
Reasoning
19/20
Coding
19/20
Instruction
18/20
Structured
14/15
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