← Back to community benchmarks
Qwen3.6-27B-oQ4-mtp
Performance
16k
tokens
679.0
PP tok/s
36.8
TG tok/s
24129
TTFT (ms)
20.7
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
64 GB
GPU Cores
40
Software
oMLX
v0.4.0
macOS
macOS 26.5
Context
16,384
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 699.7 | 44.4 | 16.8 GB | view |
| 4k | 737.1 | 42.1 | 17.6 GB | view |
| 8k | 701.6 | 39.8 | 19.2 GB | view |
| 16k | 679.0 | 36.8 | 20.7 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 44.4 | 1.00× |
| 2× | 46.5 | 1.05× |
| 4× | 58.1 | 1.31× |