← Back to community benchmarks

Qwen3.6-27B

M3 Max (40c) · 128 GB · 4bit · 2026-04-30
Performance
1k
tokens
201.7
PP tok/s
23.1
TG tok/s
5076
TTFT (ms)
15.1
Peak mem (GB)
Hardware
Chip M3 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.3.7rc2
macOS macOS 26.4.1
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 201.7 23.1 15.1 GB current
4k 182.6 20.0 16.5 GB view
16k 168.6 16.2 18.4 GB view
Batching Results
Batch Size TG tok/s Speedup
23.1 1.00×
31.1 1.35×