← Back to community benchmarks

Qwen3.6-35B-A3B-oQ8

M2 Max (38c) · 96 GB · 8bit · 2026-04-30
Performance
1k
tokens
1,136
PP tok/s
239.8
TG tok/s
902
TTFT (ms)
36.7
Peak mem (GB)
Hardware
Chip M2 Max (38c)
Memory 96 GB
GPU Cores 38
Software
oMLX v0.3.8
macOS macOS 26.4.1
Context 1,024