← Back to community benchmarks

Qwen3.5-397B-A17B

M3 Ultra (80c) · 512 GB · 8bit · 2026-03-10

Performance

1k

tokens

431.2

PP tok/s

25.7

TG tok/s

2375

TTFT (ms)

394.9

Peak mem (GB)

Hardware

Chip M3 Ultra (80c)

Memory 512 GB

GPU Cores 80

Software

oMLX v0.2.7

macOS macOS 15.7.3

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	431.2	25.7	394.9 GB	current
4k	489.9	24.9	395.2 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	25.7	1.00×
2×	38.8	1.51×
4×	53.0	2.06×