← Back to community benchmarks
Qwen3.6-27B-oQ4-mtp
Performance
16k
tokens
90.1
PP tok/s
15.3
TG tok/s
181787
TTFT (ms)
20.7
Peak mem (GB)
Hardware
Chip
M2 Max (30c)
Memory
32 GB
GPU Cores
30
Software
oMLX
v0.3.9.dev2
macOS
macOS 26.3.1
Context
16,384
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 90.6 | 19.0 | 16.8 GB | view |
| 4k | 92.3 | 18.3 | 18.2 GB | view |
| 8k | 91.8 | 16.7 | 19.2 GB | view |
| 16k | 90.1 | 15.3 | 20.7 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 19.0 | 1.00× |
| 2× | 22.2 | 1.17× |
| 4× | 44.2 | 2.33× |
| 8× | 88.3 | 4.65× |