← Back to community benchmarks
Qwen3.6-27B-oQ6-fp16-mtp
Performance
32k
tokens
605.1
PP tok/s
5.5
TG tok/s
54153
TTFT (ms)
29.6
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.3.8
macOS
macOS 26.4.1
Context
32,768
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 712.3 | 22.5 | 22.6 GB | view |
| 4k | 730.1 | 16.7 | 24.0 GB | view |
| 8k | 679.3 | 20.8 | 24.6 GB | view |
| 32k | 605.1 | 5.5 | 29.6 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 22.5 | 1.00× |
| 2× | 32.1 | 1.43× |