← Back to community benchmarks
Qwen3.6-27B-oQ6-mtp
Performance
1k
tokens
322.4
PP tok/s
10.0
TG tok/s
3176
TTFT (ms)
22.6
Peak mem (GB)
Hardware
Chip
M5 Pro (20c)
Memory
64 GB
GPU Cores
20
Software
oMLX
v0.3.9.dev2
macOS
macOS 26.5
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 322.4 | 10.0 | 22.6 GB | current |
| 4k | 313.7 | 9.1 | 24.0 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 10.0 | 1.00× |
| 2× | 15.8 | 1.58× |
| 4× | 20.5 | 2.05× |