← Back to community benchmarks
Qwen3.6-27B-oQ6-fp16-mtp
Performance
8k
tokens
603.0
PP tok/s
18.8
TG tok/s
13585
TTFT (ms)
24.9
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.3.9
macOS
macOS 26.5
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 437.9 | 18.7 | 22.4 GB | view |
| 4k | 574.6 | 18.8 | 23.8 GB | view |
| 8k | 603.0 | 18.8 | 24.9 GB | current |
| 16k | 598.1 | 18.2 | 26.4 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 18.7 | 1.00× |
| 2× | 28.9 | 1.55× |
| 4× | 34.5 | 1.84× |