GPT-120B:120b
OLLAMA GGUFgptoss · 116.8B · MXFP4
Aug 18, 2026 · Intel Core™ i7-14700F
vicuna:7b
OLLAMA GGUFllama · 7B · Q4_0
Mar 1, 2026 · Apple M4
Global Score
79 vs 59
Hardware Fit
47 vs 97
Quality Score
93 vs 43
Hardware
GPT-120B:120b vicuna:7b
MachineHP OMEN 35L VALORANT Limited Edition Gaming Desktop PCMacBook Air
CPUIntel Core™ i7-14700FApple M4
Cores2810
RAM128 GB32 GB
GPUNVIDIA GeForce RTX 5080Apple M4
OSMicrosoft Windows 11 Enterprise 10.0.26200macOS 26.3
Archx64arm64
Power Modebalancedbalanced
Performance
GPT-120B:120b vicuna:7b
Tokens/sec18.223.4
First chunk1719 msN/A
TTFT3.9 s242 ms
Load time50.9 s0.4 s
Memory usage61.5 GB5.8 GB
Memory %48%18%
HW Fit Score Breakdown
GPT-120B:120b
Speed
17/50
TTFT
5/20
Memory
25/30
vicuna:7b
Speed
37/50
TTFT
30/20
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
vicuna:7b
Reasoning
8/20
Coding
4/20
Instruction
10/20
Structured
12/15
Math
2/15
Multilingual
7/10
Reasoning: Weak Coding: Poor Instruction Following: Adequate Structured Output: Strong Math: Poor 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