← Back to community benchmarks
Qwen3.6-27B-oQ4-mtp
Performance
16k
tokens
435.4
PP tok/s
23.2
TG tok/s
37634
TTFT (ms)
20.7
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
64 GB
GPU Cores
40
Software
oMLX
v0.3.9
macOS
macOS 26.5
Context
16,384
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 355.2 | 28.2 | 16.7 GB | view |
| 4k | 436.7 | 25.2 | 18.2 GB | view |
| 8k | 463.9 | 25.9 | 19.2 GB | view |
| 16k | 435.4 | 23.2 | 20.7 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 28.2 | 1.00× |
| 2× | 29.5 | 1.05× |
| 4× | 36.8 | 1.30× |