← Back to community benchmarks

Qwen3.5-35B-A3B

M3 Max (30c) · 36 GB · 4bit · 2026-04-17
Performance
1k
tokens
926.3
PP tok/s
242.4
TG tok/s
1106
TTFT (ms)
20.6
Peak mem (GB)
Hardware
Chip M3 Max (30c)
Memory 36 GB
GPU Cores 30
Software
oMLX v0.3.6
macOS macOS 26.4.1
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 926.3 242.4 20.6 GB current
4k 340.6 81.7 20.8 GB view