← Back to community benchmarks
Qwen3.6-27B-MTPLX-Optimized-Speed
Performance
1k
tokens
42.4
PP tok/s
7.3
TG tok/s
24148
TTFT (ms)
15.8
Peak mem (GB)
Hardware
Chip
M1 Max (24c)
Memory
64 GB
GPU Cores
24
Software
oMLX
v0.3.8
macOS
macOS 26.4
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 42.4 | 7.3 | 15.8 GB | current |
| 4k | 30.7 | 7.0 | 17.3 GB | view |
| 8k | 30.0 | 6.8 | 18.3 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 7.3 | 1.00× |
| 2× | 7.6 | 1.04× |
| 4× | 8.4 | 1.15× |