← Back to community benchmarks
Qwen3.6-27B-OptiQ
Performance
8k
tokens
212.7
PP tok/s
23.1
TG tok/s
38508
TTFT (ms)
21.3
Peak mem (GB)
Hardware
Chip
M4 Max (40c)
Memory
48 GB
GPU Cores
40
Software
oMLX
v0.4.4
macOS
macOS 26.5.1
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 237.2 | 24.9 | 19.2 GB | view |
| 4k | 226.8 | 23.6 | 20.6 GB | view |
| 8k | 212.7 | 23.1 | 21.3 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 24.9 | 1.00× |
| 2× | 38.9 | 1.56× |