GPT-120B:120b
OLLAMA GGUFgptoss · 116.8B · MXFP4
Aug 18, 2026 · Intel Core™ i7-14700F
granite3.1-moe:3b
OLLAMA GGUFgranitemoe · 3.3B · Q4_K_M
May 24, 2026 · Intel Gen Intel® Core™ i7-1355U
Global Score
79 vs 66
Hardware Fit
47 vs 99
Quality Score
93 vs 52
Hardware
GPT-120B:120b granite3.1-moe:3b
MachineHP OMEN 35L VALORANT Limited Edition Gaming Desktop PCDell Inc. Inspiron 15 3530
CPUIntel Core™ i7-14700FIntel Gen Intel® Core™ i7-1355U
Cores2812
RAM128 GB31 GB
GPUNVIDIA GeForce RTX 5080Raptor Lake-P [Iris Xe Graphics]
OSMicrosoft Windows 11 Enterprise 10.0.26200cachyos rolling
Archx64x64
Power Modebalancedlow-power
Performance
GPT-120B:120b granite3.1-moe:3b
Tokens/sec18.227.2
First chunk1719 ms527 ms
TTFT3.9 s527 ms
Load time50.9 s1.9 s
Memory usage61.5 GB2.9 GB
Memory %48%9%
HW Fit Score Breakdown
GPT-120B:120b
Speed
17/50
TTFT
5/20
Memory
25/30
granite3.1-moe:3b
Speed
49/50
TTFT
20/20
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
granite3.1-moe:3b
Reasoning
7/20
Coding
9/20
Instruction
13/20
Structured
12/15
Math
5/15
Multilingual
6/10
Reasoning: Weak Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Adequate
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