← Back to community benchmarks

Qwen3.6-27BoQ8

M3 Max (40c) · 64 GB · 8bit · 2026-05-03
Performance
16k
tokens
198.2
PP tok/s
12.3
TG tok/s
82664
TTFT (ms)
32.3
Peak mem (GB)
Hardware
Chip M3 Max (40c)
Memory 64 GB
GPU Cores 40
Software
oMLX v0.3.8
macOS macOS 26.4.1
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 204.7 13.0 28.3 GB view
4k 211.6 12.8 29.8 GB view
8k 191.1 12.6 30.8 GB view
16k 198.2 12.3 32.3 GB current
Batching Results
Batch Size TG tok/s Speedup
13.0 1.00×
25.2 1.94×
38.0 2.92×