← Back to community benchmarks
Jundot--Qwen3.6-27B-oQ4-fp16-mtp
Performance
1k
tokens
360.8
PP tok/s
17.3
TG tok/s
2838
TTFT (ms)
16.4
Peak mem (GB)
Hardware
Chip
M5 Pro (16c)
Memory
48 GB
GPU Cores
16
Software
oMLX
v0.4.0
macOS
macOS 26.5
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 360.8 | 17.3 | 16.4 GB | current |
| 4k | 375.6 | 17.0 | 17.9 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 17.3 | 1.00× |
| 2× | 28.5 | 1.65× |
| 4× | 34.6 | 2.00× |