← Back to community benchmarks
Qwen3.6-27B-oQ8-mtp
Performance
1k
tokens
156.4
PP tok/s
12.8
TG tok/s
6545
TTFT (ms)
28.8
Peak mem (GB)
Hardware
Chip
M3 Ultra (60c)
Memory
256 GB
GPU Cores
60
Software
oMLX
v0.3.9
macOS
macOS 26.4.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 156.4 | 12.8 | 28.8 GB | current |
| 4k | 191.4 | 17.0 | 30.3 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 12.8 | 1.00× |
| 2× | 8.0 | 0.62× |
| 4× | 10.8 | 0.84× |