← Back to community benchmarks

Qwen3.6-35B-A3B-oQ3.5

M1 Max (24c) · 64 GB · 3bit · 2026-05-18
Performance
1k
tokens
631.9
PP tok/s
65.2
TG tok/s
1621
TTFT (ms)
17.1
Peak mem (GB)
Hardware
Chip M1 Max (24c)
Memory 64 GB
GPU Cores 24
Software
oMLX v0.3.8
macOS macOS 26.5
Context 1,024