← Back to community benchmarks
Qwen3.6-27B-OptiQ
Performance
64k
tokens
607.9
PP tok/s
22.5
TG tok/s
107805
TTFT (ms)
32.2
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.5.3
macOS
macOS 26.5.2
Context
65,536
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 897.2 | 27.5 | 19.2 GB | view |
| 4k | 936.7 | 27.4 | 20.6 GB | view |
| 8k | 876.9 | 26.9 | 21.7 GB | view |
| 16k | 760.6 | 25.4 | 23.2 GB | view |
| 32k | 664.8 | 24.7 | 26.2 GB | view |
| 64k | 607.9 | 22.5 | 32.2 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 27.5 | 1.00× |
| 2× | 53.8 | 1.96× |
| 4× | 85.7 | 3.12× |