← Back to community benchmarks
Qwen3.6-27B-oQ4-mtp
Performance
4k
tokens
795.6
PP tok/s
45.2
TG tok/s
5148
TTFT (ms)
18.2
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.4.1
macOS
macOS 26.5.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 718.5 | 42.5 | 16.8 GB | view |
| 4k | 795.6 | 45.2 | 18.2 GB | current |
| 32k | 747.8 | 37.4 | 22.6 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 42.5 | 1.00× |
| 2× | 51.0 | 1.20× |
| 4× | 66.2 | 1.56× |