GPT-20B:20b
OLLAMA GGUFgptoss · 20.9B · MXFP4
Aug 18, 2026 · Intel Core™ i7-14700F
gemma4:12b-mlx
OLLAMA GGUFJul 4, 2026 · Apple M2 Pro
Global Score
94 vs 91
Hardware Fit
96 vs 96
Quality Score
93 vs 89
Hardware
GPT-20B:20b gemma4:12b-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-20B:20b gemma4:12b-mlx
Tokens/sec181.024.7
First chunk596 ms610 ms
TTFT1.3 s610 ms
Load time10.0 s3.6 s
Memory usage11.9 GB7.1 GB
Memory %19%45%
HW Fit Score Breakdown
GPT-20B:20b
Speed
50/50
TTFT
16/20
Memory
30/30
gemma4:12b-mlx
Speed
50/50
TTFT
20/20
Memory
26/30
Quality
GPT-20B:20b
Reasoning
19/20
Coding
18/20
Instruction
16/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
gemma4:12b-mlx
Reasoning
16/20
Coding
19/20
Instruction
17/20
Structured
15/15
Math
12/15
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