← Back to community benchmarks

Qwen3.6-27B

M3 Max (40c) · 128 GB · 4bit · 2026-04-30
Performance
16k
tokens
660.3
PP tok/s
20.6
TG tok/s
24815
TTFT (ms)
19.1
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 16,384
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 view
16k 660.3 20.6 19.1 GB current
Batching Results
Batch Size TG tok/s Speedup
24.1 1.00×
34.7 1.44×