← Back to community benchmarks
Qwen3.6-27B-oQ8-mtp
Performance
4k
tokens
777.4
PP tok/s
28.9
TG tok/s
5269
TTFT (ms)
30.3
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 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 | 724.5 | 29.2 | 28.8 GB | view |
| 4k | 777.4 | 28.9 | 30.3 GB | current |
| 8k | 701.3 | 27.7 | 31.3 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 29.2 | 1.00× |
| 2× | 32.7 | 1.12× |
| 4× | 42.9 | 1.47× |