← Back to community benchmarks
Qwen3.6-27B-oQ4-fp16-mtp
Performance
8k
tokens
76.3
PP tok/s
21.7
TG tok/s
107373
TTFT (ms)
18.8
Peak mem (GB)
Hardware
Chip
M1 Max (32c)
Memory
32 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 | 76.3 | 21.7 | 18.8 GB | current |
| 16k | 147.1 | 20.6 | 20.7 GB | view |