← Back to community benchmarks

supergemma4-26b-uncensored4bit-v2

M5 Pro (20c) · 64 GB · 4bit · 2026-05-01

Performance

1k

tokens

1,547

PP tok/s

81.8

TG tok/s

662

TTFT (ms)

14.0

Peak mem (GB)

Hardware

Chip M5 Pro (20c)

Memory 64 GB

GPU Cores 20

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	1,547	81.8	14.0 GB	current
4k	1,991	77.6	14.7 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	81.8	1.00×
2×	118.6	1.45×
4×	149.5	1.83×