← Back to community benchmarks

gemma-4-26b-a4b-mxfp8

M2 Max (38c) · 64 GB · 8bit · 2026-04-05

Performance

4k

tokens

339.0

PP tok/s

27.5

TG tok/s

12085

TTFT (ms)

25.5

Peak mem (GB)

Hardware

Chip M2 Max (38c)

Memory 64 GB

GPU Cores 38

Software

oMLX v0.3.4

macOS macOS 26.4

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	327.1	27.2	25.0 GB	view
4k	339.0	27.5	25.5 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	27.2	1.00×
2×	36.9	1.36×
4×	40.5	1.49×