← Back to community benchmarks
Qwen3.6-27B
Performance
32k
tokens
83.4
PP tok/s
10.5
TG tok/s
393019
TTFT (ms)
21.6
Peak mem (GB)
Hardware
Chip
M1 Max (32c)
Memory
32 GB
GPU Cores
32
Software
oMLX
v0.3.6
macOS
macOS 26.4.1
Context
32,768
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 88.0 | 19.3 | 15.8 GB | view |
| 4k | 90.2 | 18.3 | 17.3 GB | view |
| 8k | 89.6 | 17.3 | 17.9 GB | view |
| 16k | 87.5 | 15.0 | 19.1 GB | view |
| 32k | 83.4 | 10.5 | 21.6 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 19.3 | 1.00× |
| 2× | 22.3 | 1.16× |