← Back to community benchmarks

Qwen3.5-27B-heretic-oQ4

M4 Max (40c) · 48 GB · 4bit · 2026-04-16
Performance
8k
tokens
219.1
PP tok/s
26.6
TG tok/s
37386
TTFT (ms)
18.4
Peak mem (GB)
Hardware
Chip M4 Max (40c)
Memory 48 GB
GPU Cores 40
Software
oMLX v0.3.5
macOS macOS 26.5
Context 8,192
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 view
8k 219.1 26.6 18.4 GB current
16k 227.8 25.0 19.6 GB view