GPT-120B:120b
OLLAMA GGUFgptoss · 116.8B · MXFP4
Aug 18, 2026 · Intel Core™ i7-14700F
gemma4:e4b-mlx
OLLAMA GGUFJul 7, 2026 · Apple M2 Pro
Global Score
79 vs 90
Hardware Fit
47 vs 78
Quality Score
93 vs 95
Hardware
GPT-120B:120b gemma4:e4b-mlx
MachineHP OMEN 35L VALORANT Limited Edition Gaming Desktop PCMacBook Pro
CPUIntel Core™ i7-14700FApple M2 Pro
Cores2810
RAM128 GB16 GB
GPUNVIDIA GeForce RTX 5080Apple M2 Pro
OSMicrosoft Windows 11 Enterprise 10.0.26200macOS 26.5
Archx64arm64
Power Modebalancedbalanced
Performance
GPT-120B:120b gemma4:e4b-mlx
Tokens/sec18.246.1
First chunk1719 ms284 ms
TTFT3.9 s3.9 s
Load time50.9 s0.1 s
Memory usage61.5 GB10.8 GB
Memory %48%68%
HW Fit Score Breakdown
GPT-120B:120b
Speed
17/50
TTFT
5/20
Memory
25/30
gemma4:e4b-mlx
Speed
50/50
TTFT
12/20
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
gemma4:e4b-mlx
Reasoning
19/20
Coding
19/20
Instruction
17/20
Structured
15/15
Math
15/15
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