← Back to community benchmarks
Qwen3.6-27B-oQ4-fp16-mtp
Performance
1k
tokens
106.0
PP tok/s
14.7
TG tok/s
9663
TTFT (ms)
16.7
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
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 106.0 | 14.7 | 16.7 GB | current |
| 4k | 92.2 | 14.2 | 18.2 GB | view |