← Back to community benchmarks

Qwen3.6-35B-A3B-Abliterated-Heretic

M5 Pro (20c) · 64 GB · 4bit · 2026-05-04
Performance
4k
tokens
2,022
PP tok/s
78.7
TG tok/s
2026
TTFT (ms)
24.0
Peak mem (GB)
Hardware
Chip M5 Pro (20c)
Memory 64 GB
GPU Cores 20
Software
oMLX v0.3.8
macOS macOS 26.4.1
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,340 81.8 23.1 GB view
4k 2,022 78.7 24.0 GB current
Batching Results
Batch Size TG tok/s Speedup
81.8 1.00×
162.6 1.99×
320.9 3.92×