← Back to community benchmarks
Qwen3.6-27B-MTPLX-Optimized-Speed
Performance
1k
tokens
130.9
PP tok/s
25.7
TG tok/s
7825
TTFT (ms)
29.9
Peak mem (GB)
Hardware
Chip
M1 Ultra (48c)
Memory
64 GB
GPU Cores
48
Software
oMLX
v0.4.4
macOS
macOS 26.5.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 130.9 | 25.7 | 29.9 GB | current |
| 4k | 135.2 | 22.6 | 31.4 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 25.7 | 1.00× |
| 2× | 30.7 | 1.19× |
| 4× | 33.8 | 1.32× |