← Back to community benchmarks

Qwen3.6-35B-A3B-OptiQ

M1 Max (32c) · 64 GB · 4bit · 2026-05-12
Performance
4k
tokens
603.4
PP tok/s
54.3
TG tok/s
6788
TTFT (ms)
21.6
Peak mem (GB)
Hardware
Chip M1 Max (32c)
Memory 64 GB
GPU Cores 32
Software
oMLX v0.3.9.dev1
macOS macOS 26.4.1
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 506.3 57.7 20.8 GB view
4k 603.4 54.3 21.6 GB current
8k 604.7 52.6 22.0 GB view
Batching Results
Batch Size TG tok/s Speedup
57.7 1.00×
90.6 1.57×