← Back to community benchmarks

Qwen3.6-35B-A3B-oQ6e-fp16-mtp

M2 Ultra (76c) · 192 GB · 6bit · 2026-07-19
User commentv0.5.1 5a39ba3a without custom kernels
Performance
4k
tokens
2,505
PP tok/s
82.9
TG tok/s
1635
TTFT (ms)
28.6
Peak mem (GB)
Hardware
Chip M2 Ultra (76c)
Memory 192 GB
GPU Cores 76
Software
oMLX v0.5.1
macOS macOS 26.5.2
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 2,359 83.4 27.8 GB view
4k 2,505 82.9 28.6 GB current
8k 2,391 81.5 29.0 GB view
16k 2,173 78.6 29.7 GB view
32k 1,898 74.0 31.0 GB view
64k 1,340 66.2 34.4 GB view
128k 757.8 55.9 39.8 GB view
Batching Results
Batch Size TG tok/s Speedup
83.4 1.00×
139.3 1.67×
203.0 2.43×