← Back to community benchmarks
Qwen3.6-27B-OptiQ
Performance
16k
tokens
84.1
PP tok/s
12.1
TG tok/s
194879
TTFT (ms)
21.8
Peak mem (GB)
Hardware
Chip
M1 Max (32c)
Memory
64 GB
GPU Cores
32
Software
oMLX
v0.5.2rc1
macOS
macOS 26.5.2
Context
16,384
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 88.3 | 13.6 | 19.2 GB | view |
| 16k | 84.1 | 12.1 | 21.8 GB | current |
| 64k | 66.2 | 9.7 | 26.1 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 13.6 | 1.00× |
| 2× | 16.2 | 1.19× |
| 4× | 32.6 | 2.40× |