← Back to community benchmarks

gemma-4-26b-a4b-it-mxfp8

M1 Max (32c) · 64 GB · 8bit · 2026-04-17

Performance

195k

tokens

239.4

PP tok/s

3.5

TG tok/s

835342

TTFT (ms)

35.9

Peak mem (GB)

Hardware

Chip M1 Max (32c)

Memory 64 GB

GPU Cores 32

Software

oMLX v0.3.6

macOS macOS 26.2

Context 200,000