← Back to community benchmarks

gemma-4-26b-a4b-it

M3 Ultra (80c) · 512 GB · 4bit · 2026-04-15

Performance

4k

tokens

2,097

PP tok/s

95.3

TG tok/s

1953

TTFT (ms)

14.0

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	1,540	102.4	13.5 GB	view
4k	2,097	95.3	14.0 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	102.4	1.00×
2×	160.2	1.56×
4×	233.6	2.28×