← Back to community benchmarks
Qwen3.6-27B-oQ4-fp16-mtp
Performance
16k
tokens
144.9
PP tok/s
16.8
TG tok/s
113035
TTFT (ms)
19.8
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
16,384
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 16k | 144.9 | 16.8 | 19.8 GB | current |
| 32k | 138.2 | 15.2 | 23.4 GB | view |