← Back to community benchmarks
Qwen3.6-27B-MTPLX-Optimized-Quality
Performance
8k
tokens
188.7
PP tok/s
15.3
TG tok/s
43403
TTFT (ms)
30.8
Peak mem (GB)
Hardware
Chip
M4 Max (40c)
Memory
64 GB
GPU Cores
40
Software
oMLX
v0.3.9
macOS
macOS 26.3.1
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 233.1 | 15.8 | 28.3 GB | view |
| 4k | 204.2 | 15.6 | 29.8 GB | view |
| 8k | 188.7 | 15.3 | 30.8 GB | current |
| 16k | 122.6 | 6.5 | 32.3 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 15.8 | 1.00× |
| 2× | 14.0 | 0.89× |
| 4× | 20.2 | 1.28× |
| 8× | 24.8 | 1.57× |