← Back to community benchmarks

Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled-oQ4-fp16-mtp

M1 Max (24c) · 64 GB · 4bit · 2026-06-07
Performance
64k
tokens
406.8
PP tok/s
24.3
TG tok/s
161082
TTFT (ms)
26.3
Peak mem (GB)
Hardware
Chip M1 Max (24c)
Memory 64 GB
GPU Cores 24
Software
oMLX v0.4.1
macOS macOS 26.1
Context 65,536
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
32k 633.3 32.2 23.6 GB view
64k 406.8 24.3 26.3 GB current