← Back to community benchmarks

gemma4H-31B-oQ8e

M3 Ultra (80c) · 512 GB · 8bit · 2026-07-17

Performance

64k

tokens

249.5

PP tok/s

12.6

TG tok/s

262695

TTFT (ms)

63.8

Peak mem (GB)

Hardware

Chip M3 Ultra (80c)

Memory 512 GB

GPU Cores 80

Software

oMLX v0.5.1

macOS macOS 26.5.2

Context 65,536

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	348.7	17.9	31.8 GB	view
4k	339.2	17.5	33.6 GB	view
8k	326.1	17.1	37.5 GB	view
16k	312.0	16.3	41.2 GB	view
32k	289.3	14.9	49.6 GB	view
64k	249.5	12.6	63.8 GB	current
128k	190.2	9.5	76.4 GB	view