← Back to community benchmarks

Qwen3.6-35B-A3BoQ8

M3 Max (40c) · 64 GB · 8bit · 2026-05-03
Performance
8k
tokens
1,434
PP tok/s
66.4
TG tok/s
5711
TTFT (ms)
36.5
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 8,192
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 current
16k 1,321 62.6 37.3 GB view
Batching Results
Batch Size TG tok/s Speedup
71.0 1.00×
114.2 1.61×
157.5 2.22×