← Back to community benchmarks

Qwen3.5-35B-A3B

M3 Max (40c) · 48 GB · 4bit · 2026-03-12
Performance
32k
tokens
1,153
PP tok/s
46.7
TG tok/s
28414
TTFT (ms)
21.6
Peak mem (GB)
Hardware
Chip M3 Max (40c)
Memory 48 GB
GPU Cores 40
Software
oMLX v0.2.8
macOS macOS 26.3.1
Context 32,768
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
32k 1,153 46.7 21.6 GB current
64k 852.9 32.5 23.3 GB view