← Back to community benchmarks

Qwen3.5-35B-A3B

M2 Max (30c) · 64 GB · 4bit · 2026-03-18
Performance
16k
tokens
558.1
PP tok/s
59.2
TG tok/s
29355
TTFT (ms)
20.2
Peak mem (GB)
Hardware
Chip M2 Max (30c)
Memory 64 GB
GPU Cores 30
Software
oMLX v0.2.19
macOS macOS 26.3.1
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 544.7 82.2 18.3 GB view
4k 638.3 75.7 19.2 GB view
8k 605.7 67.4 19.5 GB view
16k 558.1 59.2 20.2 GB current
32k 492.8 42.1 21.5 GB view