← Back to community benchmarks

Qwen3.5-27B-heretic-oQ4

M4 Max (40c) · 48 GB · 4bit · 2026-04-16
Performance
4k
tokens
243.1
PP tok/s
27.2
TG tok/s
16853
TTFT (ms)
17.7
Peak mem (GB)
Hardware
Chip M4 Max (40c)
Memory 48 GB
GPU Cores 40
Software
oMLX v0.3.5
macOS macOS 26.5
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 242.8 28.4 16.3 GB view
4k 243.1 27.2 17.7 GB current
8k 219.1 26.6 18.4 GB view
16k 227.8 25.0 19.6 GB view