← Back to community benchmarks
Qwen3.6-27B-oQ8-mtp
Performance
4k
tokens
862.4
PP tok/s
29.6
TG tok/s
4750
TTFT (ms)
30.3
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
64 GB
GPU Cores
40
Software
oMLX
v0.3.9
macOS
macOS 26.5
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 708.2 | 28.3 | 28.8 GB | view |
| 4k | 862.4 | 29.6 | 30.3 GB | current |
| 32k | 693.9 | 25.6 | 34.6 GB | view |
| 64k | 580.1 | 22.2 | 41.8 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 28.3 | 1.00× |
| 2× | 34.6 | 1.22× |