← Back to community benchmarks

OsaurusAI--Qwen3.6-27B

M1 Max (32c) · 32 GB · 4bit · 2026-06-15
Performance
4k
tokens
91.6
PP tok/s
16.5
TG tok/s
44695
TTFT (ms)
15.3
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 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 84.5 17.7 14.5 GB view
4k 91.6 16.5 15.3 GB current
Batching Results
Batch Size TG tok/s Speedup
17.7 1.00×
19.2 1.08×
21.2 1.20×