← Back to community benchmarks

Qwen3.5-35B-A3B

M3 Max (40c) · 128 GB · 6bit · 2026-03-09
Performance
32k
tokens
944.5
PP tok/s
49.2
TG tok/s
34692
TTFT (ms)
29.7
Peak mem (GB)
Hardware
Chip M3 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.2.6
macOS macOS 26.3
Context 32,768
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
8k 1,355 63.8 28.5 GB view
16k 1,216 61.1 28.9 GB view
32k 944.5 49.2 29.7 GB current
64k 727.1 39.5 31.4 GB view