← Back to community benchmarks

gemma-4-26B-A4B-it-heretic

M5 Pro (20c) · 48 GB · 4bit · 2026-04-30

Performance

195k

tokens

665.6

PP tok/s

15.1

TG tok/s

300489

TTFT (ms)

24.9

Peak mem (GB)

Hardware

Chip M5 Pro (20c)

Memory 48 GB

GPU Cores 20

Software

oMLX v0.3.8

macOS macOS 26.4.1

Context 200,000

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	1,337	68.2	14.3 GB	view
4k	1,776	65.5	14.9 GB	view
195k	665.6	15.1	24.9 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	68.2	1.00×
2×	102.6	1.50×
4×	123.6	1.81×