← Back to community benchmarks

gemma-4-26b-a4b-it-mxfp8

M3 Ultra (60c) · 96 GB · 8bit · 2026-04-15

Performance

1k

tokens

1,008

PP tok/s

76.2

TG tok/s

1016

TTFT (ms)

25.0

Peak mem (GB)

Hardware

Chip M3 Ultra (60c)

Memory 96 GB

GPU Cores 60

Software

oMLX v0.3.5

macOS macOS 26.3.1

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	1,008	76.2	25.0 GB	current
4k	1,409	72.8	25.4 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	76.2	1.00×
2×	108.2	1.42×
4×	137.4	1.80×