gemma4:e4b-mlx
OLLAMA GGUFJul 7, 2026 · Apple M2 Pro
GPT-OSS-20B:20b
OLLAMA GGUFgptoss · 20.9B · MXFP4
Aug 18, 2026 · Intel Core™ i7-14700F
Global Score
90 vs 93
Hardware Fit
78 vs 92
Quality Score
95 vs 93
Hardware
gemma4:e4b-mlx GPT-OSS-20B:20b
MachineMacBook ProHP OMEN 35L VALORANT Limited Edition Gaming Desktop PC
CPUApple M2 ProIntel Core™ i7-14700F
Cores1028
RAM16 GB128 GB
GPUApple M2 ProNVIDIA GeForce RTX 5080
OSmacOS 26.5Microsoft Windows 11 Enterprise 10.0.26200
Archarm64x64
Power Modebalancedbalanced
Performance
gemma4:e4b-mlx GPT-OSS-20B:20b
Tokens/sec46.1178.6
First chunk284 ms695 ms
TTFT3.9 s1.4 s
Load time0.1 s31.2 s
Memory usage10.8 GB11.9 GB
Memory %68%9%
HW Fit Score Breakdown
gemma4:e4b-mlx
Speed
50/50
TTFT
12/20
Memory
16/30
GPT-OSS-20B:20b
Speed
50/50
TTFT
12/20
Memory
30/30
Quality
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
GPT-OSS-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
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