← Back to community benchmarks
Qwen3.6-27B-oQ6-mtp
Performance
16k
tokens
736.3
PP tok/s
29.4
TG tok/s
22253
TTFT (ms)
26.9
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.3.9
macOS
macOS 26.3.1
Context
16,384
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 663.3 | 32.6 | 23.0 GB | view |
| 4k | 734.9 | 31.6 | 24.4 GB | view |
| 8k | 751.9 | 31.0 | 25.4 GB | view |
| 16k | 736.3 | 29.4 | 26.9 GB | current |
| 32k | 683.2 | 27.2 | 29.9 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 32.6 | 1.00× |
| 2× | 37.1 | 1.14× |
| 4× | 45.7 | 1.40× |
| 8× | 50.2 | 1.54× |