← Back to community benchmarks
Qwen3.6-27B-UD
Performance
1k
tokens
788.8
PP tok/s
21.6
TG tok/s
1298
TTFT (ms)
25.2
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.3.8rc1
macOS
macOS 26.4
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 788.8 | 21.6 | 25.2 GB | current |
| 4k | 929.8 | 21.1 | 26.6 GB | view |
| 8k | 877.6 | 20.1 | 27.2 GB | view |
| 16k | 790.4 | 19.7 | 28.5 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 21.6 | 1.00× |
| 2× | 24.1 | 1.12× |
| 4× | 40.2 | 1.86× |