← Back to community benchmarks
Qwen3.6-27B-oQ4-fp16-mtp
Performance
8k
tokens
152.2
PP tok/s
20.0
TG tok/s
53823
TTFT (ms)
18.8
Peak mem (GB)
Hardware
Chip
M2 Max (30c)
Memory
32 GB
GPU Cores
30
Software
oMLX
v0.4.0
macOS
macOS 14.6
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 141.4 | 16.0 | 16.5 GB | view |
| 4k | 150.9 | 19.9 | 17.6 GB | view |
| 8k | 152.2 | 20.0 | 18.8 GB | current |
| 16k | 149.6 | 19.2 | 20.0 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 16.0 | 1.00× |
| 2× | 23.7 | 1.48× |
| 4× | 47.3 | 2.96× |