← Back to community benchmarks
Qwen3.6-27B-oQ8-mtp
Performance
16k
tokens
705.3
PP tok/s
24.4
TG tok/s
23231
TTFT (ms)
32.8
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
16,384
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 706.7 | 26.2 | 28.8 GB | view |
| 4k | 760.1 | 28.3 | 30.3 GB | view |
| 8k | 702.0 | 26.5 | 31.3 GB | view |
| 16k | 705.3 | 24.4 | 32.8 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 26.2 | 1.00× |
| 2× | 27.5 | 1.05× |
| 4× | 43.5 | 1.66× |