← Back to community benchmarks

Qwen3.6-35B-A3B-uncensored-heretic-Native-MTP-Preserved

M5 Max (40c) · 128 GB · fp16 · 2026-07-25
Performance
128k
tokens
1,348
PP tok/s
47.9
TG tok/s
97272
TTFT (ms)
76.9
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.5.3
macOS macOS 27.0
Context 131,072
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 3,060 71.0 65.8 GB view
4k 4,276 70.4 66.6 GB view
8k 3,882 69.2 66.9 GB view
16k 3,533 64.1 67.6 GB view
32k 2,883 63.0 68.9 GB view
64k 2,188 57.0 71.5 GB view
128k 1,348 47.9 76.9 GB current
Batching Results
Batch Size TG tok/s Speedup
71.0 1.00×
67.8 0.95×
119.4 1.68×