← Back to community benchmarks

Qwen3.5-27B

M4 Max (40c) · 64 GB · 4bit · 2026-03-09
Performance
8k
tokens
186.4
PP tok/s
20.3
TG tok/s
43959
TTFT (ms)
17.4
Peak mem (GB)
Hardware
Chip M4 Max (40c)
Memory 64 GB
GPU Cores 40
Software
oMLX v0.2.6
macOS macOS 26.3
Context 8,192
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 239.4 27.6 16.6 GB view
4k 199.2 23.6 17.0 GB view
8k 186.4 20.3 17.4 GB current
Batching Results
Batch Size TG tok/s Speedup
27.6 1.00×
40.4 1.46×