← Back to community benchmarks

Qwen3.6-35B-A3B-oQ6-mtp

M1 Ultra (64c) · 128 GB · 6bit · 2026-05-19
Performance
4k
tokens
1,028
PP tok/s
51.7
TG tok/s
3983
TTFT (ms)
28.4
Peak mem (GB)
Hardware
Chip M1 Ultra (64c)
Memory 128 GB
GPU Cores 64
Software
oMLX v0.3.9rc1
macOS macOS 26.5
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 755.4 52.6 27.7 GB view
4k 1,028 51.7 28.4 GB current
8k 1,057 50.3 28.9 GB view
16k 1,029 46.5 29.6 GB view
Batching Results
Batch Size TG tok/s Speedup
52.6 1.00×
87.6 1.67×
133.7 2.54×