← Back to community benchmarks

gemma-4-26B-A4B-it-uncensored-heretic-ara8bit-int8-affine

M5 Max (40c) · 128 GB · 8bit · 2026-05-27

Performance

64k

tokens

1,792

PP tok/s

45.0

TG tok/s

36581

TTFT (ms)

30.6

Peak mem (GB)

Hardware

Chip M5 Max (40c)

Memory 128 GB

GPU Cores 40

Software

oMLX v0.3.12

macOS macOS 26.5

Context 65,536