← Back to community benchmarks

Huihui-Qwen3.6-35B-A3B-Claude-4.7-Opus-abliterated-vmxfp8

M5 Pro (20c) · 64 GB · 8bit · 2026-07-19
Performance
16k
tokens
2,175
PP tok/s
59.1
TG tok/s
7533
TTFT (ms)
36.6
Peak mem (GB)
Hardware
Chip M5 Pro (20c)
Memory 64 GB
GPU Cores 20
Software
oMLX v0.5.1
macOS macOS 26.5.2
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
4k 2,420 63.9 35.1 GB view
8k 2,366 61.2 35.7 GB view
16k 2,175 59.1 36.6 GB current
32k 1,827 53.4 38.4 GB view
64k 1,331 45.8 41.0 GB view