← Back to community benchmarks
Qwen3.6-27B-oQ4-mtp
Performance
32k
tokens
410.1
PP tok/s
21.7
TG tok/s
79903
TTFT (ms)
23.7
Peak mem (GB)
Hardware
Chip
M5 Pro (20c)
Memory
48 GB
GPU Cores
20
Software
oMLX
v0.3.9.dev2
macOS
macOS 26.5
Context
32,768
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 430.0 | 26.2 | 16.8 GB | view |
| 4k | 466.0 | 24.5 | 18.2 GB | view |
| 8k | 453.5 | 24.8 | 19.2 GB | view |
| 16k | 437.7 | 23.8 | 20.7 GB | view |
| 32k | 410.1 | 21.7 | 23.7 GB | current |
| 64k | 338.8 | 18.0 | 29.8 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 26.2 | 1.00× |
| 2× | 31.2 | 1.19× |
| 4× | 41.5 | 1.58× |