← Back to community benchmarks
Qwen3.6-27B-MTP
Performance
4k
tokens
823.2
PP tok/s
44.4
TG tok/s
4976
TTFT (ms)
17.5
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.3.9.dev2
macOS
macOS 26.5
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 737.3 | 40.3 | 16.1 GB | view |
| 4k | 823.2 | 44.4 | 17.5 GB | current |
| 8k | 787.8 | 44.9 | 18.5 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 40.3 | 1.00× |
| 2× | 55.1 | 1.37× |
| 4× | 74.0 | 1.84× |