Google

Google

Google/Gemma 4 E2B

Quantizations

Quant	Quantized by	Size	Decode	Prefill	Score	Actions
4bit	MLX Community MLX Community	3.3 GB	N/A	N/A	N/A	Run
5bit	MLX Community MLX Community	3.9 GB	N/A	N/A	N/A	Run
mxfp4	MLX Community MLX Community	4.0 GB	70.6 tok/s	1,965.1 tok/s	Runs great	Run
nvfp4	MLX Community MLX Community	4.1 GB	72.9 tok/s	2,279.7 tok/s	Runs great	Run
6bit	MLX Community MLX Community	4.4 GB	N/A	N/A	N/A	Run
8bit	MLX Community MLX Community	5.5 GB	68.7 tok/s	1,939.8 tok/s	Runs great	Run

Device Comparison

Results include trials with 4,096 input tokens and 1,024 output tokens only.