← Back to community benchmarks
Qwen3.6-27B
Performance
32k
tokens
578.4
PP tok/s
13.6
TG tok/s
56652
TTFT (ms)
38.9
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.3.8.dev1
macOS
macOS 26.4.1
Context
32,768
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 568.0 | 15.6 | 33.0 GB | view |
| 4k | 798.4 | 15.4 | 34.6 GB | view |
| 8k | 758.4 | 14.9 | 35.2 GB | view |
| 16k | 654.7 | 14.1 | 36.4 GB | view |
| 32k | 578.4 | 13.6 | 38.9 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 15.6 | 1.00× |
| 2× | 19.0 | 1.22× |
| 4× | 30.2 | 1.94× |
| 8× | 42.6 | 2.73× |