← Back to community benchmarks

Qwen3.6-35B-A3B-YOYO-V2-oQ4e-mtp

M5 Max (40c) · 128 GB · 4bit · 2026-07-17
Performance
4k
tokens
4,005
PP tok/s
114.8
TG tok/s
1023
TTFT (ms)
20.7
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.5.1
macOS macOS 26.5.2
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 3,400 115.7 19.9 GB view
4k 4,005 114.8 20.7 GB current
64k 2,354 83.8 25.8 GB view
Batching Results
Batch Size TG tok/s Speedup
115.7 1.00×
187.7 1.62×
290.9 2.51×