← Back to community benchmarks

Qwen3.5-27B

M4 Pro (16c) · 64 GB · 4bit · 2026-03-10
Performance
8k
tokens
100.9
PP tok/s
14.0
TG tok/s
81197
TTFT (ms)
17.4
Peak mem (GB)
Hardware
Chip M4 Pro (16c)
Memory 64 GB
GPU Cores 16
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 102.6 15.3 16.6 GB view
4k 102.6 14.6 17.0 GB view
8k 100.9 14.0 17.4 GB current
Batching Results
Batch Size TG tok/s Speedup
15.3 1.00×
25.1 1.64×
27.0 1.76×