← Back to community benchmarks

gemma-4-26b-a4b-it-oQ4

M2 Max (30c) · 64 GB · 4bit · 2026-04-17

Performance

4k

tokens

467.6

PP tok/s

52.7

TG tok/s

8761

TTFT (ms)

14.9

Peak mem (GB)

Hardware

Chip M2 Max (30c)

Memory 64 GB

GPU Cores 30

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	457.9	57.4	14.4 GB	view
4k	467.6	52.7	14.9 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	57.4	1.00×
2×	68.0	1.18×
4×	76.9	1.34×