← Back to community benchmarks

Qwen3.6-35B-A3B

M5 Max (40c) · 128 GB · 8bit · 2026-04-24
Performance
16k
tokens
3,755
PP tok/s
83.2
TG tok/s
4363
TTFT (ms)
37.1
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.3.6
macOS macOS 26.4.1
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
16k 3,755 83.2 37.1 GB current
32k 3,173 71.3 38.5 GB view