← Back to community benchmarks

Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled-oQ6-fp16-mtp

M2 Ultra (60c) · 64 GB · 6bit · 2026-06-07
Performance
8k
tokens
1,765
PP tok/s
58.6
TG tok/s
4641
TTFT (ms)
28.9
Peak mem (GB)
Hardware
Chip M2 Ultra (60c)
Memory 64 GB
GPU Cores 60
Software
oMLX v0.4.2rc1
macOS macOS 15.7.7
Context 8,192
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,354 63.1 27.8 GB view
4k 1,835 58.5 28.6 GB view
8k 1,765 58.6 28.9 GB current
16k 1,594 54.8 29.6 GB view
32k 1,377 50.3 30.9 GB view
64k 926.3 36.5 33.6 GB view
Batching Results
Batch Size TG tok/s Speedup
63.1 1.00×
57.1 0.90×
122.9 1.95×