← Back to community benchmarks
Qwen3.6-27B-oQ4-mtp
Performance
8k
tokens
143.7
PP tok/s
17.6
TG tok/s
57015
TTFT (ms)
19.2
Peak mem (GB)
Hardware
Chip
M3 Max (30c)
Memory
36 GB
GPU Cores
30
Software
oMLX
v0.3.9.dev2
macOS
macOS 26.5
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 158.2 | 25.5 | 16.7 GB | view |
| 4k | 152.1 | 21.5 | 18.2 GB | view |
| 8k | 143.7 | 17.6 | 19.2 GB | current |
| 16k | 106.6 | 8.5 | 20.7 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 25.5 | 1.00× |
| 2× | 13.3 | 0.52× |
| 4× | 20.9 | 0.82× |