← Back to community benchmarks
Qwen3.6-27B-oQ4-fp16-mtp
Performance
16k
tokens
296.8
PP tok/s
34.7
TG tok/s
55205
TTFT (ms)
20.7
Peak mem (GB)
Hardware
Chip
M2 Ultra (60c)
Memory
128 GB
GPU Cores
60
Software
oMLX
v0.3.9.dev2
macOS
macOS 15.6.1
Context
16,384
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 8k | 303.5 | 36.3 | 18.8 GB | view |
| 16k | 296.8 | 34.7 | 20.7 GB | current |