← Back to community benchmarks
Qwen3.6-27B-oQ6-fp16-mtp
Performance
16k
tokens
711.4
PP tok/s
30.2
TG tok/s
23029
TTFT (ms)
26.7
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.3.9
macOS
macOS 26.5
Context
16,384
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 752.4 | 30.4 | 22.8 GB | view |
| 4k | 828.3 | 33.2 | 24.2 GB | view |
| 8k | 773.2 | 31.1 | 25.2 GB | view |
| 16k | 711.4 | 30.2 | 26.7 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 30.4 | 1.00× |
| 2× | 37.3 | 1.23× |
| 4× | 41.9 | 1.38× |