← Back to community benchmarks

Qwen3.6-35B-A3BoQ8

M3 Max (40c) · 64 GB · 8bit · 2026-05-03
Performance
16k
tokens
1,321
PP tok/s
62.6
TG tok/s
12408
TTFT (ms)
37.3
Peak mem (GB)
Hardware
Chip M3 Max (40c)
Memory 64 GB
GPU Cores 40
Software
oMLX v0.3.8
macOS macOS 26.4.1
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,116 71.0 35.3 GB view
4k 1,431 70.2 36.1 GB view
8k 1,434 66.4 36.5 GB view
16k 1,321 62.6 37.3 GB current
Batching Results
Batch Size TG tok/s Speedup
71.0 1.00×
114.2 1.61×
157.5 2.22×