← Back to community benchmarks

Qwen3.6-27B-UD

M5 Pro (16c) · 48 GB · 4bit · 2026-06-04
Performance
4k
tokens
361.8
PP tok/s
11.0
TG tok/s
11320
TTFT (ms)
26.1
Peak mem (GB)
Hardware
Chip M5 Pro (16c)
Memory 48 GB
GPU Cores 16
Software
oMLX v0.4.0rc1
macOS macOS 26.5.1
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 339.2 11.2 24.8 GB view
4k 361.8 11.0 26.1 GB current
Batching Results
Batch Size TG tok/s Speedup
11.2 1.00×
12.5 1.12×
20.2 1.80×