← Back to community benchmarks
Qwen3.6-27B-oQ4-mtp
Performance
8k
tokens
726.2
PP tok/s
39.7
TG tok/s
11280
TTFT (ms)
19.2
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
64 GB
GPU Cores
40
Software
oMLX
v0.3.9rc1
macOS
macOS 26.5
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 787.5 | 48.3 | 16.7 GB | view |
| 4k | 791.2 | 43.4 | 18.2 GB | view |
| 8k | 726.2 | 39.7 | 19.2 GB | current |
| 16k | 668.4 | 40.3 | 20.7 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 48.3 | 1.00× |
| 2× | 51.7 | 1.07× |
| 4× | 59.9 | 1.24× |