← Back to community benchmarks

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

M5 Max (40c) · 64 GB · 4bit · 2026-04-18
Performance
1k
tokens
823.0
PP tok/s
131.3
TG tok/s
1244
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 823.0 131.3 18.7 GB current
16k 770.4 30.6 18.4 GB view
32k 659.9 25.5 20.9 GB view