← Back to community benchmarks

Qwen3.5-35B-A3B-oQ4e

M3 Ultra (60c) · 256 GB · 4bit · 2026-04-17
Performance
1k
tokens
1,748
PP tok/s
339.5
TG tok/s
586
TTFT (ms)
21.2
Peak mem (GB)
Hardware
Chip M3 Ultra (60c)
Memory 256 GB
GPU Cores 60
Software
oMLX v0.3.6
macOS macOS 15.7.3
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,748 339.5 21.2 GB current
4k 657.1 90.6 23.0 GB view
8k 2,098 88.4 23.4 GB view