← Back to community benchmarks

Qwen3.5-27B

M4 Pro (20c) · 64 GB · 4bit · 2026-03-09
Performance
1k
tokens
126.8
PP tok/s
15.3
TG tok/s
8076
TTFT (ms)
16.6
Peak mem (GB)
Hardware
Chip M4 Pro (20c)
Memory 64 GB
GPU Cores 20
Software
oMLX v0.2.6
macOS macOS 26.2
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 126.8 15.3 16.6 GB current
4k 121.4 15.0 17.0 GB view
Batching Results
Batch Size TG tok/s Speedup
15.3 1.00×
29.6 1.93×
32.7 2.14×
33.5 2.19×