← Back to community benchmarks

supergemma4-26b-uncensored4bit-v2

M1 Ultra (48c) · 64 GB · 4bit · 2026-04-16

Performance

4k

tokens

680.2

PP tok/s

59.0

TG tok/s

6022

TTFT (ms)

14.4

Peak mem (GB)

Hardware

Chip M1 Ultra (48c)

Memory 64 GB

GPU Cores 48

Software

oMLX v0.3.5

macOS macOS 26.2

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	594.6	63.5	14.0 GB	view
4k	680.2	59.0	14.4 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	63.5	1.00×
2×	69.5	1.09×
4×	106.0	1.67×