← Back to community benchmarks
Qwen3.6-35B-A3B-Hereticmixed-6.4bit
Performance
1k
tokens
634.8
PP tok/s
60.0
TG tok/s
1613
TTFT (ms)
26.6
Peak mem (GB)
Hardware
Chip
M4 Pro (16c)
Memory
48 GB
GPU Cores
16
Software
oMLX
v0.3.6
macOS
macOS 26.4.1
Context
1,024