← Back to community benchmarks
Qwen3.6-27B
Performance
8k
tokens
809.7
PP tok/s
32.3
TG tok/s
10118
TTFT (ms)
17.1
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.4.1
macOS
macOS 26.5.1
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 765.8 | 33.4 | 15.1 GB | view |
| 4k | 870.9 | 32.9 | 16.5 GB | view |
| 8k | 809.7 | 32.3 | 17.1 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 33.4 | 1.00× |
| 2× | 57.6 | 1.72× |
| 4× | 66.6 | 1.99× |