← Back to community benchmarks

Qwen3.6-35B-A3BoQ4

M1 Max (24c) · 64 GB · 4bit · 2026-04-17
User commenttemp=0.7, top_p=0.8, top_k=20, min_p=0.0, pp=1.5, rp=1.0/no-thinking
Performance
32k
tokens
631.6
PP tok/s
40.6
TG tok/s
51879
TTFT (ms)
23.1
Peak mem (GB)
Hardware
Chip M1 Max (24c)
Memory 64 GB
GPU Cores 24
Software
oMLX v0.3.6
macOS macOS 26.3.1
Context 32,768