← Back to community benchmarks
Qwen3.6-27B-oQ4-mtp
Performance
16k
tokens
439.6
PP tok/s
16.1
TG tok/s
37272
TTFT (ms)
20.4
Peak mem (GB)
Hardware
Chip
M5 Pro (20c)
Memory
64 GB
GPU Cores
20
Software
oMLX
v0.3.9.dev2
macOS
macOS 26.4
Context
16,384
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 427.1 | 17.4 | 16.4 GB | view |
| 4k | 468.1 | 17.0 | 17.9 GB | view |
| 8k | 466.7 | 16.7 | 18.9 GB | view |
| 16k | 439.6 | 16.1 | 20.4 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 17.4 | 1.00× |
| 2× | 30.9 | 1.78× |
| 4× | 40.9 | 2.35× |