← Back to community benchmarks

Qwen3.5-27B

M5 Pro (20c) · 48 GB · 4bit · 2026-04-14
Performance
1k
tokens
413.3
PP tok/s
17.4
TG tok/s
2478
TTFT (ms)
15.8
Peak mem (GB)
Hardware
Chip M5 Pro (20c)
Memory 48 GB
GPU Cores 20
Software
oMLX v0.3.5
macOS macOS 26.4.1
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 413.3 17.4 15.8 GB current
4k 452.1 17.0 17.3 GB view
Batching Results
Batch Size TG tok/s Speedup
17.4 1.00×
30.0 1.72×
39.1 2.25×