← Back to community benchmarks
Qwen3.6-27B-oQ4-mtp
Performance
16k
tokens
88.4
PP tok/s
15.2
TG tok/s
185398
TTFT (ms)
20.0
Peak mem (GB)
Hardware
Chip
M2 Max (30c)
Memory
32 GB
GPU Cores
30
Software
oMLX
v0.4.0
macOS
macOS 14.6
Context
16,384
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 86.8 | 12.8 | 16.5 GB | view |
| 4k | 88.4 | 16.2 | 17.7 GB | view |
| 8k | 90.0 | 16.1 | 18.8 GB | view |
| 16k | 88.4 | 15.2 | 20.0 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 12.8 | 1.00× |
| 2× | 18.2 | 1.42× |
| 4× | 36.6 | 2.86× |