← Back to community benchmarks
Qwen3.6-27B-OptiQ
Performance
1k
tokens
194.2
PP tok/s
20.6
TG tok/s
5272
TTFT (ms)
17.1
Peak mem (GB)
Hardware
Chip
M4 Max (32c)
Memory
36 GB
GPU Cores
32
Software
oMLX
v0.3.6
macOS
macOS 26.4.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 194.2 | 20.6 | 17.1 GB | current |
| 4k | 200.7 | 19.8 | 18.5 GB | view |
| 8k | 190.9 | 18.5 | 19.1 GB | view |
| 16k | 190.5 | 17.1 | 20.4 GB | view |
| 32k | 159.8 | 14.3 | 22.9 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 20.6 | 1.00× |
| 2× | 32.7 | 1.59× |
| 4× | 40.2 | 1.95× |