← Back to community benchmarks
Qwen3.6-27B-MTPLX-Optimized
Performance
195k
tokens
317.2
PP tok/s
10.4
TG tok/s
630481
TTFT (ms)
51.5
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.3.8
macOS
macOS 26.4
Context
200,000
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 766.6 | 27.4 | 19.6 GB | view |
| 4k | 889.6 | 27.1 | 21.1 GB | view |
| 195k | 317.2 | 10.4 | 51.5 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 27.4 | 1.00× |
| 2× | 45.6 | 1.66× |
| 4× | 60.9 | 2.22× |