← Back to community benchmarks
Qwen3.6-27B-MTPLX-Optimized-Quality
Performance
1k
tokens
88.6
PP tok/s
11.5
TG tok/s
11552
TTFT (ms)
28.3
Peak mem (GB)
Hardware
Chip
M1 Max (32c)
Memory
64 GB
GPU Cores
32
Software
oMLX
v0.3.9.dev2
macOS
macOS 26.5
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 88.6 | 11.5 | 28.3 GB | current |
| 4k | 90.3 | 11.3 | 29.8 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 11.5 | 1.00× |
| 2× | 19.9 | 1.73× |
| 4× | 39.9 | 3.47× |