← Back to community benchmarks

gemma-4-26b-ud-4bit

M1 Max (32c) · 64 GB · 4bit · 2026-05-12

Performance

1k

tokens

445.0

PP tok/s

51.4

TG tok/s

2301

TTFT (ms)

14.7

Peak mem (GB)

Hardware

Chip M1 Max (32c)

Memory 64 GB

GPU Cores 32

Software

oMLX v0.3.8

macOS macOS 26.4.1

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	445.0	51.4	14.7 GB	current
4k	480.8	49.1	15.3 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	51.4	1.00×
2×	102.3	1.99×
4×	203.3	3.96×