← Back to community benchmarks

Qwen3.6-27B

M1 Max (32c) · 64 GB · 8bit · 2026-04-23
Performance
32k
tokens
93.3
PP tok/s
7.7
TG tok/s
351246
TTFT (ms)
38.9
Peak mem (GB)
Hardware
Chip M1 Max (32c)
Memory 64 GB
GPU Cores 32
Software
oMLX v0.3.7rc2
macOS macOS 26.4.1
Context 32,768
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 96.7 9.7 33.0 GB view
4k 99.6 9.5 34.6 GB view
32k 93.3 7.7 38.9 GB current
64k 83.1 6.2 44.0 GB view
Batching Results
Batch Size TG tok/s Speedup
9.7 1.00×
11.3 1.16×
16.6 1.71×