← Back to community benchmarks

Qwen3.5-35B-A3B-Claude-4.6-Opus-Reasoning-Distilled

M4 Max (40c) · 128 GB · 8bit · 2026-04-16
Performance
4k
tokens
889.7
PP tok/s
84.1
TG tok/s
4604
TTFT (ms)
36.2
Peak mem (GB)
Hardware
Chip M4 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.3.5
macOS macOS 15.7.5
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,203 309.4 36.7 GB view
4k 889.7 84.1 36.2 GB current