← Back to community benchmarks
Youssofal--Qwen3.6-27B-MTPLX-Optimized-Speed
Performance
4k
tokens
166.8
PP tok/s
20.7
TG tok/s
24559
TTFT (ms)
17.3
Peak mem (GB)
Hardware
Chip
M3 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.3.8
macOS
macOS 26.5
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 200.1 | 21.5 | 15.8 GB | view |
| 4k | 166.8 | 20.7 | 17.3 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 21.5 | 1.00× |
| 2× | 30.8 | 1.43× |
| 4× | 39.5 | 1.84× |