← Back to community benchmarks
Qwen3.6-27B-oQ6-fp16-mtp
Performance
4k
tokens
725.7
PP tok/s
31.6
TG tok/s
5644
TTFT (ms)
24.4
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
64 GB
GPU Cores
40
Software
oMLX
v0.3.9.dev2
macOS
macOS 26.4.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 749.9 | 34.7 | 23.0 GB | view |
| 4k | 725.7 | 31.6 | 24.4 GB | current |
| 8k | 664.5 | 29.2 | 25.4 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 34.7 | 1.00× |
| 2× | 34.3 | 0.99× |
| 4× | 41.0 | 1.18× |