← Back to community benchmarks
Qwen3.6-27B-oQ4-mtp
Performance
4k
tokens
440.5
PP tok/s
16.8
TG tok/s
9299
TTFT (ms)
17.9
Peak mem (GB)
Hardware
Chip
M5 Pro (20c)
Memory
64 GB
GPU Cores
20
Software
oMLX
v0.3.9
macOS
macOS 26.5
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 423.5 | 16.9 | 16.4 GB | view |
| 4k | 440.5 | 16.8 | 17.9 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 16.9 | 1.00× |
| 2× | 32.3 | 1.91× |
| 4× | 67.5 | 3.99× |