Back to leaderboard

gemma4:e4b-mlx

OLLAMA GGUF
Excellent

Jul 7, 2026 · Apple M2 Pro

GPT-OSS-20B:20b

OLLAMA GGUF

gptoss · 20.9B · MXFP4

Excellent

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
$ metrillm

Requires Node 20+ and Ollama or LM Studio running

Or run without installing: npx metrillm@latest