← Back to community benchmarks

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

M1 Ultra (64c) · 128 GB · 6bit · 2026-05-19
Performance
8k
tokens
1,053
PP tok/s
55.6
TG tok/s
7781
TTFT (ms)
29.6
Peak mem (GB)
Hardware
Chip M1 Ultra (64c)
Memory 128 GB
GPU Cores 64
Software
oMLX v0.3.9rc1
macOS macOS 26.5
Context 8,192
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 745.8 60.4 28.3 GB view
4k 1,025 58.1 29.1 GB view
8k 1,053 55.6 29.6 GB current
16k 1,033 53.5 30.3 GB view
Batching Results
Batch Size TG tok/s Speedup
60.4 1.00×
87.5 1.45×
108.5 1.80×