← Back to community benchmarks

gemma-4-26b-a4b

M4 (10c) · 32 GB · 4bit · 2026-04-30

Performance

4k

tokens

374.8

PP tok/s

30.1

TG tok/s

10930

TTFT (ms)

15.0

Peak mem (GB)

Hardware

Chip M4 (10c)

Memory 32 GB

GPU Cores 10

Software

oMLX v0.3.2

macOS macOS 26.4.1

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	387.8	31.2	14.6 GB	view
4k	374.8	30.1	15.0 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	31.2	1.00×
2×	32.9	1.05×
4×	35.2	1.13×