← Back to community benchmarks
Qwen3.6-27B-oQ6-mtp
Performance
1k
tokens
117.7
PP tok/s
15.7
TG tok/s
8702
TTFT (ms)
23.0
Peak mem (GB)
Hardware
Chip
M4 Pro (20c)
Memory
64 GB
GPU Cores
20
Software
oMLX
v0.3.9.dev1
macOS
macOS 26.4.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 117.7 | 15.7 | 23.0 GB | current |
| 4k | 112.0 | 14.4 | 24.4 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 15.7 | 1.00× |
| 2× | 16.4 | 1.04× |
| 4× | 17.8 | 1.13× |