← Back to community benchmarks
Qwen3.6-27B-oQ4-mtp
Performance
32k
tokens
154.8
PP tok/s
16.8
TG tok/s
211708
TTFT (ms)
23.7
Peak mem (GB)
Hardware
Chip
M3 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.3.9.dev1
macOS
macOS 26.4.1
Context
32,768
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 166.8 | 21.4 | 16.8 GB | view |
| 4k | 168.3 | 19.6 | 18.2 GB | view |
| 8k | 172.8 | 20.2 | 19.2 GB | view |
| 16k | 170.3 | 18.9 | 20.7 GB | view |
| 32k | 154.8 | 16.8 | 23.7 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 21.4 | 1.00× |
| 2× | 23.5 | 1.10× |
| 4× | 29.5 | 1.38× |