← Back to community benchmarks

gemma-4-26b-a4b

M5 Pro (20c) · 48 GB · 4bit · 2026-06-04

Performance

1k

tokens

1,094

PP tok/s

72.9

TG tok/s

937

TTFT (ms)

13.6

Peak mem (GB)

Hardware

Chip M5 Pro (20c)

Memory 48 GB

GPU Cores 20

Software

oMLX v0.4.1

macOS macOS 26.5

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	1,094	72.9	13.6 GB	current
4k	1,908	70.2	14.2 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	72.9	1.00×
2×	103.7	1.42×
4×	127.2	1.74×