← Back to community benchmarks
Qwen3.6-27B-oQ4-mtp
Performance
1k
tokens
306.1
PP tok/s
46.4
TG tok/s
3346
TTFT (ms)
16.9
Peak mem (GB)
Hardware
Chip
M3 Ultra (60c)
Memory
256 GB
GPU Cores
60
Software
oMLX
v0.3.9.dev2
macOS
macOS 26.4.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 306.1 | 46.4 | 16.9 GB | current |
| 4k | 323.0 | 45.2 | 18.4 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 46.4 | 1.00× |
| 2× | 60.8 | 1.31× |
| 4× | 69.3 | 1.49× |