← Back to community benchmarks

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

M1 Pro (14c) · 32 GB · 4bit · 2026-04-17

Performance

4k

tokens

222.9

PP tok/s

31.9

TG tok/s

18377

TTFT (ms)

14.7

Peak mem (GB)

Hardware

Chip M1 Pro (14c)

Memory 32 GB

GPU Cores 14

Software

oMLX v0.3.6

macOS macOS 26.4.1

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	214.3	34.3	14.2 GB	view
4k	222.9	31.9	14.7 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	34.3	1.00×
2×	39.4	1.15×
4×	42.9	1.25×