← Back to community benchmarks
Qwen3.6-27B-oQ6-fp16-mtp
Performance
8k
tokens
137.7
PP tok/s
16.3
TG tok/s
59506
TTFT (ms)
25.0
Peak mem (GB)
Hardware
Chip
M1 Max (32c)
Memory
64 GB
GPU Cores
32
Software
oMLX
v0.3.9.dev2
macOS
macOS 26.4.1
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 8k | 137.7 | 16.3 | 25.0 GB | current |
| 16k | 135.6 | 15.2 | 26.9 GB | view |