← Back to community benchmarks

gemma-4-26b-a4b-it

M1 Max (24c) · 64 GB · 4bit · 2026-04-20

Performance

4k

tokens

349.5

PP tok/s

41.8

TG tok/s

11720

TTFT (ms)

14.7

Peak mem (GB)

Hardware

Chip M1 Max (24c)

Memory 64 GB

GPU Cores 24

Software

oMLX v0.3.6

macOS macOS 15.7.5

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	316.7	48.1	14.2 GB	view
4k	349.5	41.8	14.7 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	48.1	1.00×
2×	59.6	1.24×
4×	65.8	1.37×