← Back to community benchmarks

SuperGemma4-26b-uncensored4bit-v2

M2 Max (30c) · 64 GB · 4bit · 2026-04-17

Performance

1k

tokens

456.8

PP tok/s

66.5

TG tok/s

2242

TTFT (ms)

14.0

Peak mem (GB)

Hardware

Chip M2 Max (30c)

Memory 64 GB

GPU Cores 30

Software

oMLX v0.3.6

macOS macOS 15.7.5

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	456.8	66.5	14.0 GB	current
4k	477.0	60.8	14.4 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	66.5	1.00×
2×	80.0	1.20×
4×	87.1	1.31×