← Back to community benchmarks
Qwen3.6-27B-MXFP4-MTP
Performance
4k
tokens
370.4
PP tok/s
12.9
TG tok/s
11058
TTFT (ms)
16.7
Peak mem (GB)
Hardware
Chip
M5 Pro (16c)
Memory
48 GB
GPU Cores
16
Software
oMLX
v0.3.9.dev2
macOS
macOS 26.5
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 346.9 | 12.3 | 15.3 GB | view |
| 4k | 370.4 | 12.9 | 16.7 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 12.3 | 1.00× |
| 2× | 29.4 | 2.39× |
| 4× | 33.5 | 2.72× |