← Back to community benchmarks
Qwen3.6-27B
Performance
8k
tokens
28.9
PP tok/s
5.0
TG tok/s
283525
TTFT (ms)
24.6
Peak mem (GB)
Hardware
Chip
M1 Max (24c)
Memory
64 GB
GPU Cores
24
Software
oMLX
v0.3.8
macOS
macOS 26.4
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 25.7 | 4.9 | 22.1 GB | view |
| 4k | 27.4 | 5.3 | 23.5 GB | view |
| 8k | 28.9 | 5.0 | 24.6 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 4.9 | 1.00× |
| 2× | 5.6 | 1.14× |
| 4× | 6.3 | 1.29× |