← Back to community benchmarks
Qwen3.6-27B-oQ4-fp16-mtp
Performance
4k
tokens
97.3
PP tok/s
14.8
TG tok/s
42110
TTFT (ms)
18.2
Peak mem (GB)
Hardware
Chip
M1 Max (32c)
Memory
64 GB
GPU Cores
32
Software
oMLX
v0.3.9.dev2
macOS
macOS 26.5
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 117.0 | 15.6 | 16.7 GB | view |
| 4k | 97.3 | 14.8 | 18.2 GB | current |