← Back to community benchmarks

gemma-4-26b-a4b-it

M3 Ultra (80c) · 512 GB · 8bit · 2026-04-15

Performance

4k

tokens

2,074

PP tok/s

76.1

TG tok/s

1975

TTFT (ms)

26.2

Peak mem (GB)

Hardware

Chip M3 Ultra (80c)

Memory 512 GB

GPU Cores 80

Software

oMLX v0.3.5.dev1

macOS macOS 26.4

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	1,517	80.9	25.7 GB	view
4k	2,074	76.1	26.2 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	80.9	1.00×
2×	123.5	1.53×
4×	9.2	0.11×