← Back to community benchmarks

gemma-4-e4b-it-mxfp8

M4 (8c) · 16 GB · 8bit · 2026-04-06

Performance

4k

tokens

463.2

PP tok/s

19.0

TG tok/s

8842

TTFT (ms)

7.8

Peak mem (GB)

Hardware

Chip M4 (8c)

Memory 16 GB

GPU Cores 8

Software

oMLX v0.3.4

macOS macOS 26.4

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	425.5	18.6	7.7 GB	view
4k	463.2	19.0	7.8 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	18.6	1.00×
2×	27.5	1.48×
4×	28.8	1.55×