← Back to community benchmarks
qwen3.6-dense-27b-mtp
Performance
8k
tokens
840.4
PP tok/s
44.1
TG tok/s
9748
TTFT (ms)
19.2
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.3.9.dev1
macOS
macOS 26.4.1
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 785.3 | 46.6 | 16.8 GB | view |
| 4k | 888.6 | 45.3 | 18.2 GB | view |
| 8k | 840.4 | 44.1 | 19.2 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 46.6 | 1.00× |
| 2× | 55.5 | 1.19× |
| 4× | 70.0 | 1.50× |
| 8× | 71.2 | 1.53× |