← Back to community benchmarks

Huihui-Qwen3.6-35B-A3B-Claude-4.7-Opus-abliterated-v

M5 Pro (20c) · 64 GB · 4bit · 2026-05-10
Performance
16k
tokens
4,351
PP tok/s
94.7
TG tok/s
3766
TTFT (ms)
22.5
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 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,503 102.1 20.1 GB view
4k 2,207 98.5 20.9 GB view
8k 2,289 94.1 21.4 GB view
16k 4,351 94.7 22.5 GB current
32k 4,299 90.8 23.0 GB view
64k 3,794 76.3 23.9 GB view
Batching Results
Batch Size TG tok/s Speedup
102.1 1.00×
153.5 1.50×
194.9 1.91×
594.8 5.83×