← Back to community benchmarks
Qwen3.6-27B-MXFP4-MTP
Performance
4k
tokens
836.3
PP tok/s
24.7
TG tok/s
4898
TTFT (ms)
17.3
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 GB
GPU Cores
40
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 | 766.5 | 25.1 | 15.9 GB | view |
| 4k | 836.3 | 24.7 | 17.3 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 25.1 | 1.00× |
| 2× | 59.6 | 2.37× |
| 4× | 72.9 | 2.90× |