← Back to community benchmarks
Qwen3.6-27B-mtp
Performance
8k
tokens
800.2
PP tok/s
29.1
TG tok/s
10237
TTFT (ms)
33.4
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
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 724.7 | 27.5 | 30.9 GB | view |
| 4k | 840.5 | 29.1 | 32.4 GB | view |
| 8k | 800.2 | 29.1 | 33.4 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 27.5 | 1.00× |
| 2× | 34.9 | 1.27× |
| 4× | 47.6 | 1.73× |
| 8× | 54.7 | 1.99× |