← Back to community benchmarks
Qwen3.6-27B4bit-MTP
Performance
1k
tokens
431.9
PP tok/s
25.3
TG tok/s
2371
TTFT (ms)
16.1
Peak mem (GB)
Hardware
Chip
M5 Pro (20c)
Memory
48 GB
GPU Cores
20
Software
oMLX
v0.3.9rc1
macOS
macOS 26.5
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 431.9 | 25.3 | 16.1 GB | current |
| 4k | 473.3 | 25.6 | 17.5 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 25.3 | 1.00× |
| 2× | 31.2 | 1.23× |
| 4× | 44.0 | 1.74× |