GPT-120B:120b
OLLAMA GGUFgptoss · 116.8B · MXFP4
Aug 18, 2026 · Intel Core™ i7-14700F
google/gemma-4-e4b
LM-STUDIO GGUFgemma4 · Q4_K_M
Jul 7, 2026 · AMD Ryzen 7 5800H
Global Score
79 vs 62
Hardware Fit
47 vs 77
Quality Score
93 vs 55
Hardware
GPT-120B:120b google/gemma-4-e4b
MachineHP OMEN 35L VALORANT Limited Edition Gaming Desktop PCLENOVO 82JQ
CPUIntel Core™ i7-14700FAMD Ryzen 7 5800H
Cores2816
RAM128 GB16 GB
GPUNVIDIA GeForce RTX 5080NVIDIA GeForce RTX 3060 Laptop GPU
OSMicrosoft Windows 11 Enterprise 10.0.26200Microsoft Windows 11 家庭版 中文版 10.0.26100
Archx64x64
Power Modebalancedbalanced
Performance
GPT-120B:120b google/gemma-4-e4b
Tokens/sec18.227.6
First chunk1719 ms23 ms
TTFT3.9 s480 ms
Load time50.9 sN/A
Memory usage61.5 GB13.2 GB
Memory %48%83%
HW Fit Score Breakdown
GPT-120B:120b
Speed
17/50
TTFT
5/20
Memory
25/30
google/gemma-4-e4b
Speed
48/50
TTFT
20/20
Memory
9/30
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
google/gemma-4-e4b
Reasoning
18/20
Coding
17/20
Instruction
5/20
Structured
3/15
Math
11/15
Multilingual
1/10
Reasoning: Strong Coding: Strong Instruction Following: Weak Structured Output: Poor Math: Strong Multilingual: Poor
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