← Back to community benchmarks

Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled-oQ3-mtp

M2 Max (38c) · 32 GB · 3bit · 2026-05-14
Performance
4k
tokens
403.7
PP tok/s
77.5
TG tok/s
10146
TTFT (ms)
16.7
Peak mem (GB)
Hardware
Chip M2 Max (38c)
Memory 32 GB
GPU Cores 38
Software
oMLX v0.3.8
macOS macOS 26.4.1
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 552.9 10.8 17.9 GB view
4k 403.7 77.5 16.7 GB current