← Back to community benchmarks

granite-4.1-8b-mxfp8

M2 Pro (16c) · 16 GB · 8bit · 2026-05-01

Performance

1k

tokens

156.4

PP tok/s

19.5

TG tok/s

6548

TTFT (ms)

9.2

Peak mem (GB)

Hardware

Chip M2 Pro (16c)

Memory 16 GB

GPU Cores 16

Software

oMLX v0.3.7rc2

macOS macOS 26.4.1

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	156.4	19.5	9.2 GB	current
4k	152.6	17.2	9.7 GB	view
8k	143.9	14.6	10.3 GB	view