← Back to community benchmarks
Qwen3.6-27B-oQ4-mtp
Performance
1k
tokens
100.6
PP tok/s
14.9
TG tok/s
10181
TTFT (ms)
16.5
Peak mem (GB)
Hardware
Chip
M4 Pro (16c)
Memory
48 GB
GPU Cores
16
Software
oMLX
v0.3.9.dev1
macOS
macOS 26.2
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 100.6 | 14.9 | 16.5 GB | current |
| 4k | 101.5 | 14.4 | 17.9 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 14.9 | 1.00× |
| 2× | 22.6 | 1.52× |
| 4× | 23.8 | 1.60× |