← Back to community benchmarks
Qwen3.6-27B
Performance
8k
tokens
198.1
PP tok/s
19.8
TG tok/s
41343
TTFT (ms)
18.3
Peak mem (GB)
Hardware
Chip
M4 Max (32c)
Memory
36 GB
GPU Cores
32
Software
oMLX
v0.4.1
macOS
macOS 15.7.7
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 189.1 | 20.9 | 15.4 GB | view |
| 4k | 197.5 | 20.5 | 16.7 GB | view |
| 8k | 198.1 | 19.8 | 18.3 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 20.9 | 1.00× |
| 2× | 40.6 | 1.94× |
| 4× | 48.3 | 2.31× |