← Back to community benchmarks

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

M4 Pro (16c) · 48 GB · 4bit · 2026-06-07
Performance
64k
tokens
445.4
PP tok/s
39.4
TG tok/s
147140
TTFT (ms)
26.2
Peak mem (GB)
Hardware
Chip M4 Pro (16c)
Memory 48 GB
GPU Cores 16
Software
oMLX v0.4.2rc1
macOS macOS 26.5.1
Context 65,536
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 682.7 65.7 20.4 GB view
64k 445.4 39.4 26.2 GB current
128k 294.8 28.8 30.8 GB view
Batching Results
Batch Size TG tok/s Speedup
65.7 1.00×
125.3 1.91×