← Back to community benchmarks

gemma-4-26b-a4b-it

M1 Ultra (48c) · 128 GB · 8bit · 2026-04-05

Performance

1k

tokens

697.8

PP tok/s

34.1

TG tok/s

1467

TTFT (ms)

26.8

Peak mem (GB)

Hardware

Chip M1 Ultra (48c)

Memory 128 GB

GPU Cores 48

Software

oMLX v0.3.2

macOS macOS 15.7.2

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	697.8	34.1	26.8 GB	current
4k	691.4	35.0	27.3 GB	view
8k	665.2	32.1	27.4 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	34.1	1.00×
2×	55.1	1.62×
4×	82.5	2.42×