← Back to community benchmarks

Qwen3.5-35B-A3B

M1 Max (24c) · 32 GB · 3bit · 2026-05-11
Performance
1k
tokens
613.3
PP tok/s
54.4
TG tok/s
1670
TTFT (ms)
19.7
Peak mem (GB)
Hardware
Chip M1 Max (24c)
Memory 32 GB
GPU Cores 24
Software
oMLX v0.3.8
macOS macOS 26.3.1
Context 1,024