← Back to community benchmarks
Qwen3.6-27B-mtp
Performance
4k
tokens
188.1
PP tok/s
12.0
TG tok/s
21775
TTFT (ms)
29.8
Peak mem (GB)
Hardware
Chip
M3 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.3.8
macOS
macOS 26.4.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 204.2 | 12.5 | 28.3 GB | view |
| 4k | 188.1 | 12.0 | 29.8 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 12.5 | 1.00× |
| 2× | 19.3 | 1.54× |
| 4× | 28.0 | 2.24× |