← Back to community benchmarks
Qwen3.6-27B-oQ6-fp16-mtp
Performance
8k
tokens
679.3
PP tok/s
20.8
TG tok/s
12060
TTFT (ms)
24.6
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
8,192
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 | current |
| 32k | 605.1 | 5.5 | 29.6 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 22.5 | 1.00× |
| 2× | 32.1 | 1.43× |