← Back to community benchmarks
Qwen3.6-27B-oQ4-fp16-mtp
Performance
16k
tokens
151.8
PP tok/s
19.3
TG tok/s
107953
TTFT (ms)
20.7
Peak mem (GB)
Hardware
Chip
M2 Max (30c)
Memory
32 GB
GPU Cores
30
Software
oMLX
v0.3.9
macOS
macOS 26.3.1
Context
16,384
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 152.7 | 24.4 | 16.7 GB | view |
| 4k | 157.4 | 23.7 | 18.2 GB | view |
| 8k | 156.3 | 21.2 | 19.2 GB | view |
| 16k | 151.8 | 19.3 | 20.7 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 24.4 | 1.00× |
| 2× | 29.0 | 1.19× |
| 4× | 56.7 | 2.32× |
| 8× | 113.4 | 4.65× |