← Back to community benchmarks

Qwen3.6-35B-A3B

M5 Max (40c) · 128 GB · bf16 · 2026-04-16
Performance
64k
tokens
2,289
PP tok/s
39.8
TG tok/s
28633
TTFT (ms)
71.3
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.3.6
macOS macOS 26.4.1
Context 65,536
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,872 72.4 65.6 GB view
4k 3,401 70.5 66.4 GB view
16k 3,547 65.1 67.4 GB view
64k 2,289 39.8 71.3 GB current
Batching Results
Batch Size TG tok/s Speedup
72.4 1.00×
78.2 1.08×
133.5 1.84×