← Back to community benchmarks
Qwen3.6-27B-oQ4-mtp
Performance
4k
tokens
126.7
PP tok/s
16.7
TG tok/s
32329
TTFT (ms)
18.2
Peak mem (GB)
Hardware
Chip
M3 Max (30c)
Memory
36 GB
GPU Cores
30
Software
oMLX
v0.3.9.dev2
macOS
macOS 26.5
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 118.6 | 14.3 | 16.7 GB | view |
| 4k | 126.7 | 16.7 | 18.2 GB | current |
| 8k | 136.6 | 17.7 | 19.2 GB | view |
| 16k | 135.0 | 16.4 | 20.7 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 14.3 | 1.00× |
| 2× | 18.2 | 1.27× |