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
66 vs 85
Hardware Fit
14 vs 95
Quality Score
88 vs 81
Hardware
GPT-120B:120b gemma4:e4b-mlx
MachineHP OMEN 35L VALORANT Limited Edition Gaming Desktop PCMacBook Pro
CPUIntel Core™ i7-14700FApple M2 Pro
Cores2810
RAM64 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/sec10.147.3
First chunk6562 ms258 ms
TTFT10.3 s258 ms
Load time49.8 s5.1 s
Memory usage61.5 GB7.9 GB
Memory %96%49%
HW Fit Score Breakdown
GPT-120B:120b
Speed
10/50
TTFT
2/20
Memory
2/30
gemma4:e4b-mlx
Speed
50/50
TTFT
20/20
Memory
25/30
Quality
GPT-120B:120b
Reasoning
18/20
Coding
19/20
Instruction
11/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong
gemma4:e4b-mlx
Reasoning
15/20
Coding
18/20
Instruction
15/20
Structured
15/15
Math
8/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate 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