← Back to community benchmarks

Qwen3.6-35B-A3B-Claude-4.6-Opus-Reasoning-Distilled

M4 Max (40c) · 64 GB · 6bit · 2026-05-10
Performance
1k
tokens
1,259
PP tok/s
94.4
TG tok/s
814
TTFT (ms)
27.3
Peak mem (GB)
Hardware
Chip M4 Max (40c)
Memory 64 GB
GPU Cores 40
Software
oMLX v0.3.9.dev1
macOS macOS 26.4.1
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,259 94.4 27.3 GB current
4k 1,662 92.1 28.1 GB view
8k 1,668 89.3 28.6 GB view
16k 1,566 82.6 29.3 GB view
32k 1,354 75.8 30.8 GB view
Batching Results
Batch Size TG tok/s Speedup
94.4 1.00×
144.2 1.53×
197.4 2.09×