← Back to community benchmarks

gemma-4-26b-a4b-it

M5 Max (40c) · 128 GB · 6bit · 2026-04-06

Performance

1k

tokens

1,734

PP tok/s

95.5

TG tok/s

591

TTFT (ms)

20.0

Peak mem (GB)

Hardware

Chip M5 Max (40c)

Memory 128 GB

GPU Cores 40

Software

oMLX v0.3.4

macOS macOS 26.4

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	1,734	95.5	20.0 GB	current
4k	2,968	89.8	20.5 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	95.5	1.00×
2×	189.4	1.98×
4×	372.5	3.90×