← Back to community benchmarks
Qwen3.6-27B-mtp
Performance
1k
tokens
529.1
PP tok/s
39.1
TG tok/s
1935
TTFT (ms)
16.1
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
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 529.1 | 39.1 | 16.1 GB | current |
| 4k | 624.3 | 44.1 | 17.6 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 39.1 | 1.00× |
| 2× | 50.8 | 1.30× |
| 4× | 75.7 | 1.94× |