← Back to community benchmarks
Qwen3.6-27B-oQ6-mtp
Performance
16k
tokens
756.1
PP tok/s
29.4
TG tok/s
21669
TTFT (ms)
27.2
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.3.9.dev1
macOS
macOS 26.5
Context
16,384
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 740.4 | 33.7 | 23.2 GB | view |
| 4k | 821.6 | 32.3 | 24.6 GB | view |
| 8k | 784.4 | 31.4 | 25.7 GB | view |
| 16k | 756.1 | 29.4 | 27.2 GB | current |
| 32k | 696.2 | 28.1 | 30.2 GB | view |
| 64k | 587.9 | 24.6 | 36.2 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 33.7 | 1.00× |
| 2× | 37.5 | 1.11× |
| 4× | 47.5 | 1.41× |