← Back to community benchmarks
Qwen3.6-27B-oQ8-mtp
Performance
8k
tokens
680.6
PP tok/s
27.2
TG tok/s
12036
TTFT (ms)
31.3
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
64 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 | 724.1 | 29.7 | 28.8 GB | view |
| 4k | 740.5 | 29.3 | 30.3 GB | view |
| 8k | 680.6 | 27.2 | 31.3 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 29.7 | 1.00× |
| 2× | 33.0 | 1.11× |
| 4× | 45.3 | 1.53× |