← Back to community benchmarks

Qwen3.5-397B-A17B-8bit-gs32

M3 Ultra (80c) · 512 GB · 8bit · 2026-03-11
Performance
8k
tokens
489.6
PP tok/s
24.4
TG tok/s
16731
TTFT (ms)
417.8
Peak mem (GB)
Hardware
Chip M3 Ultra (80c)
Memory 512 GB
GPU Cores 80
Software
oMLX v0.2.6
macOS macOS 26.2
Context 8,192
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 416.8 26.1 417.1 GB view
4k 487.0 25.5 417.4 GB view
8k 489.6 24.4 417.8 GB current
16k 473.2 22.3 418.5 GB view
32k 432.9 19.2 420.0 GB view