← Back to community benchmarks

Qwen3.6-35B-A3B

M2 Max (38c) · 96 GB · 8bit · 2026-04-17
Performance
32k
tokens
667.1
PP tok/s
42.3
TG tok/s
49118
TTFT (ms)
38.5
Peak mem (GB)
Hardware
Chip M2 Max (38c)
Memory 96 GB
GPU Cores 38
Software
oMLX v0.3.6
macOS macOS 26.4.1
Context 32,768
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
32k 667.1 42.3 38.5 GB current
64k 552.7 32.1 41.2 GB view