← Back to community benchmarks
Qwen3.6-27B-oQ4-mtp
Performance
32k
tokens
189.0
PP tok/s
11.4
TG tok/s
173381
TTFT (ms)
22.4
Peak mem (GB)
Hardware
Chip
M5 (10c)
Memory
32 GB
GPU Cores
10
Software
oMLX
v0.3.9.dev2
macOS
macOS 26.4.1
Context
32,768
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 218.2 | 13.5 | 16.6 GB | view |
| 4k | 228.8 | 13.9 | 18.1 GB | view |
| 32k | 189.0 | 11.4 | 22.4 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 13.5 | 1.00× |
| 2× | 16.4 | 1.21× |
| 4× | 21.5 | 1.59× |