← Back to community benchmarks

Qwen3.6-35B-A3B

M1 Max (32c) · 32 GB · 4bit · 2026-04-23
Performance
1k
tokens
450.8
PP tok/s
66.9
TG tok/s
2271
TTFT (ms)
19.3
Peak mem (GB)
Hardware
Chip M1 Max (32c)
Memory 32 GB
GPU Cores 32
Software
oMLX v0.3.7
macOS macOS 26.2
Context 1,024