← Back to community benchmarks

Qwen3.6-35B-A3B-oQ4-mtp

M4 Max (40c) · 128 GB · 4bit · 2026-05-19
Performance
16k
tokens
1,566
PP tok/s
95.2
TG tok/s
10464
TTFT (ms)
22.1
Peak mem (GB)
Hardware
Chip M4 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.3.9.dev2
macOS macOS 26.4.1
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,348 111.3 20.4 GB view
4k 1,696 105.9 21.2 GB view
16k 1,566 95.2 22.1 GB current
Batching Results
Batch Size TG tok/s Speedup
111.3 1.00×
174.7 1.57×
236.5 2.12×