← Back to community benchmarks

Qwen3.6-27B

M3 Max (40c) · 128 GB · 4bit · 2026-04-30
Performance
4k
tokens
194.6
PP tok/s
22.0
TG tok/s
21048
TTFT (ms)
16.9
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 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 207.4 24.1 15.4 GB view
4k 194.6 22.0 16.9 GB current
16k 660.3 20.6 19.1 GB view
Batching Results
Batch Size TG tok/s Speedup
24.1 1.00×
34.7 1.44×