← Back to community benchmarks

Qwen3.6-35B-A3B-5bit

M1 Max (24c) · 32 GB · 5bit · 2026-04-19
Performance
8k
tokens
437.4
PP tok/s
46.2
TG tok/s
18729
TTFT (ms)
24.4
Peak mem (GB)
Hardware
Chip M1 Max (24c)
Memory 32 GB
GPU Cores 24
Software
oMLX v0.3.6
macOS macOS 26.3
Context 8,192