← Back to community benchmarks

Qwen3.6-35B-A3B-oQ4

M1 Max (32c) · 64 GB · 4bit · 2026-04-18
Performance
16k
tokens
859.7
PP tok/s
22.0
TG tok/s
19059
TTFT (ms)
22.9
Peak mem (GB)
Hardware
Chip M1 Max (32c)
Memory 64 GB
GPU Cores 32
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 859.7 22.0 22.9 GB current
32k 786.7 21.6 23.6 GB view