← Back to community benchmarks

OsaurusAI--Qwen3.6-27B

M1 Max (32c) · 32 GB · 4bit · 2026-06-15
Performance
1k
tokens
84.5
PP tok/s
17.7
TG tok/s
12113
TTFT (ms)
14.5
Peak mem (GB)
Hardware
Chip M1 Max (32c)
Memory 32 GB
GPU Cores 32
Software
oMLX v0.4.1
macOS macOS 15.7.7
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 84.5 17.7 14.5 GB current
4k 91.6 16.5 15.3 GB view
Batching Results
Batch Size TG tok/s Speedup
1× 17.7 1.00×
2× 19.2 1.08×
4× 21.2 1.20×