← Back to community benchmarks

Qwen3.6-35B-A3BoQ5

M3 Max (40c) · 128 GB · 5bit · 2026-04-27
Performance
4k
tokens
845.5
PP tok/s
74.7
TG tok/s
4844
TTFT (ms)
24.6
Peak mem (GB)
Hardware
Chip M3 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.3.7
macOS macOS 26.5
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,192 259.0 25.2 GB view
4k 845.5 74.7 24.6 GB current