← Back to community benchmarks
Qwen3.6-27B-oQ8-mtp
Performance
1k
tokens
298.5
PP tok/s
32.0
TG tok/s
3430
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
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 32.0 | 1.00× |
| 2× | 39.4 | 1.23× |
| 4× | 78.6 | 2.46× |