← Back to community benchmarks

Qwen3.6-35B-A3B

M1 Max (32c) · 64 GB · 8bit · 2026-05-01
Performance
8k
tokens
593.2
PP tok/s
49.0
TG tok/s
13809
TTFT (ms)
36.7
Peak mem (GB)
Hardware
Chip M1 Max (32c)
Memory 64 GB
GPU Cores 32
Software
oMLX v0.3.8
macOS macOS 15.7.3
Context 8,192
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
4k 591.5 51.7 36.2 GB view
8k 593.2 49.0 36.7 GB current
16k 571.8 45.0 37.4 GB view
32k 520.5 40.1 38.9 GB view
64k 419.4 31.5 41.9 GB view