← Back to community benchmarks

Qwen3.5-27B-Architect-Polaris-Heretic-mxfp4

M5 Max (40c) · 64 GB · 4bit · 2026-04-18
Performance
1k
tokens
565.5
PP tok/s
120.7
TG tok/s
1811
TTFT (ms)
18.7
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 64 GB
GPU Cores 40
Software
oMLX v0.3.6
macOS macOS 26.4.1
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 565.5 120.7 18.7 GB current
4k 573.9 33.6 16.5 GB view
8k 677.0 32.7 17.1 GB view
16k 654.1 29.3 18.4 GB view
32k 583.1 21.8 20.9 GB view