← Back to community benchmarks
Qwen3.6-27B-MXFP8-MTP
Performance
4k
tokens
396.2
PP tok/s
10.4
TG tok/s
10339
TTFT (ms)
32.5
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.3.9.dev2
macOS
macOS 26.4.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 450.6 | 11.2 | 29.5 GB | view |
| 4k | 396.2 | 10.4 | 32.5 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 11.2 | 1.00× |
| 2× | 21.6 | 1.93× |
| 4× | 26.1 | 2.33× |
| 8× | 30.2 | 2.70× |