← Back to community benchmarks
Qwen3.6-27B-oQ8-mtp
Performance
16k
tokens
801.4
PP tok/s
17.4
TG tok/s
20445
TTFT (ms)
32.1
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
64 GB
GPU Cores
40
Software
oMLX
v0.3.9.dev1
macOS
macOS 26.4.1
Context
16,384
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 731.7 | 18.4 | 28.3 GB | view |
| 4k | 876.3 | 18.3 | 29.8 GB | view |
| 16k | 801.4 | 17.4 | 32.1 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 18.4 | 1.00× |
| 2× | 35.7 | 1.94× |
| 4× | 47.0 | 2.55× |