← Back to community benchmarks
Qwen3.6-27B-oQ4-mtp
Performance
1k
tokens
116.6
PP tok/s
22.3
TG tok/s
8784
TTFT (ms)
16.7
Peak mem (GB)
Hardware
Chip
M4 Pro (20c)
Memory
48 GB
GPU Cores
20
Software
oMLX
v0.3.9.dev2
macOS
macOS 26.5
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 116.6 | 22.3 | 16.7 GB | current |
| 4k | 121.1 | 21.5 | 18.2 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 22.3 | 1.00× |
| 2× | 26.5 | 1.19× |