← Back to community benchmarks
Qwen3.6-27BoQ4
Performance
8k
tokens
151.5
PP tok/s
18.6
TG tok/s
54084
TTFT (ms)
18.7
Peak mem (GB)
Hardware
Chip
M1 Max (32c)
Memory
64 GB
GPU Cores
32
Software
oMLX
v0.3.8.dev1
macOS
macOS 26.1
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 122.7 | 19.8 | 16.6 GB | view |
| 4k | 150.2 | 18.9 | 18.1 GB | view |
| 8k | 151.5 | 18.6 | 18.7 GB | current |
| 16k | 147.4 | 16.7 | 19.9 GB | view |
| 32k | 139.2 | 13.3 | 22.4 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 19.8 | 1.00× |
| 2× | 28.8 | 1.45× |