← Back to community benchmarks
Qwen3.6-27B-UD
Performance
4k
tokens
67.6
PP tok/s
9.3
TG tok/s
60631
TTFT (ms)
26.6
Peak mem (GB)
Hardware
Chip
M1 Max (24c)
Memory
64 GB
GPU Cores
24
Software
oMLX
v0.3.8
macOS
macOS 26.3.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 69.0 | 9.4 | 25.2 GB | view |
| 4k | 67.6 | 9.3 | 26.6 GB | current |
| 8k | 69.5 | 9.3 | 27.6 GB | view |
| 16k | 69.2 | 9.0 | 29.1 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 9.4 | 1.00× |
| 2× | 8.5 | 0.90× |
| 4× | 12.6 | 1.34× |
| 8× | 13.7 | 1.46× |