← 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
8k
tokens
2,289
PP tok/s
94.1
TG tok/s
3579
TTFT (ms)
21.4
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 8,192
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 current
16k 4,351 94.7 22.5 GB view
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×