← Back to community benchmarks
Qwen3.6-27B-oQ8-fp16-mtp
Performance
1k
tokens
291.1
PP tok/s
21.0
TG tok/s
3518
TTFT (ms)
28.3
Peak mem (GB)
Hardware
Chip
M2 Ultra (60c)
Memory
192 GB
GPU Cores
60
Software
oMLX
v0.3.9.dev2
macOS
macOS 26.3.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 291.1 | 21.0 | 28.3 GB | current |
| 4k | 314.0 | 20.7 | 29.8 GB | view |