← Back to community benchmarks
Qwen3.6-27B-oQ4-mtp
Performance
8k
tokens
87.9
PP tok/s
15.6
TG tok/s
93192
TTFT (ms)
19.2
Peak mem (GB)
Hardware
Chip
M1 Max (32c)
Memory
64 GB
GPU Cores
32
Software
oMLX
v0.3.9.dev2
macOS
macOS 15.7.5
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 86.5 | 16.9 | 16.7 GB | view |
| 4k | 88.4 | 16.4 | 18.2 GB | view |
| 8k | 87.9 | 15.6 | 19.2 GB | current |
| 16k | 74.7 | 12.7 | 20.7 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 16.9 | 1.00× |
| 2× | 16.2 | 0.96× |
| 4× | 17.4 | 1.03× |