← Back to community benchmarks

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

M1 Max (32c) · 64 GB · 8bit · 2026-04-15

Performance

8k

tokens

596.1

PP tok/s

47.5

TG tok/s

13743

TTFT (ms)

36.8

Peak mem (GB)

Hardware

Chip M1 Max (32c)

Memory 64 GB

GPU Cores 32

Software

oMLX v0.3.5

macOS macOS 26.2

Context 8,192