← Back to community benchmarks
Qwen3.6-27B-oQ4-fp16-mtp
Performance
16k
tokens
152.1
PP tok/s
19.3
TG tok/s
107705
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 | 153.2 | 24.1 | 16.7 GB | view |
| 4k | 157.5 | 24.2 | 18.3 GB | view |
| 8k | 156.2 | 23.2 | 19.2 GB | view |
| 16k | 152.1 | 19.3 | 20.7 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 24.1 | 1.00× |
| 2× | 28.9 | 1.20× |
| 4× | 56.8 | 2.36× |
| 8× | 115.8 | 4.80× |