← Back to community benchmarks

gemma-4-26B-A4B-it-Claude-Opus-Distilled-v23bit-int3-affine

M4 (10c) · 24 GB · 3bit · 2026-05-20

Performance

64k

tokens

153.4

PP tok/s

11.4

TG tok/s

427321

TTFT (ms)

16.2

Peak mem (GB)

Hardware

Chip M4 (10c)

Memory 24 GB

GPU Cores 10

Software

oMLX v0.3.9.dev2

macOS macOS 26.4.1

Context 65,536