← Back to community benchmarks
Qwen3.6-27B
Performance
16k
tokens
138.6
PP tok/s
3.5
TG tok/s
118201
TTFT (ms)
36.4
Peak mem (GB)
Hardware
Chip
M3 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.3.6
macOS
macOS 26.4.1
Context
16,384
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 209.3 | 11.0 | 33.0 GB | view |
| 4k | 179.3 | 9.0 | 34.6 GB | view |
| 8k | 167.0 | 9.3 | 35.2 GB | view |
| 16k | 138.6 | 3.5 | 36.4 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 11.0 | 1.00× |
| 2× | 4.9 | 0.45× |
| 4× | 6.9 | 0.63× |