← Back to community benchmarks
Qwen3.6-27B-OptiQ
Performance
1k
tokens
222.3
PP tok/s
24.0
TG tok/s
4606
TTFT (ms)
18.9
Peak mem (GB)
Hardware
Chip
M4 Max (40c)
Memory
48 GB
GPU Cores
40
Software
oMLX
v0.4.1
macOS
macOS 26.4.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 222.3 | 24.0 | 18.9 GB | current |
| 4k | 244.8 | 23.8 | 20.1 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 24.0 | 1.00× |
| 2× | 45.3 | 1.89× |
| 4× | 55.2 | 2.30× |
| 8× | 109.1 | 4.55× |