← Back to community benchmarks
Qwen3.6-27B-oQ4-fp16-mtp
Performance
16k
tokens
662.4
PP tok/s
40.5
TG tok/s
24733
TTFT (ms)
20.7
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
64 GB
GPU Cores
40
Software
oMLX
v0.3.9rc1
macOS
macOS 26.5
Context
16,384
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 799.2 | 47.7 | 16.7 GB | view |
| 4k | 825.8 | 43.4 | 18.2 GB | view |
| 8k | 722.9 | 40.3 | 19.2 GB | view |
| 16k | 662.4 | 40.5 | 20.7 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 47.7 | 1.00× |
| 2× | 52.2 | 1.09× |
| 4× | 60.7 | 1.27× |