← Back to community benchmarks
Qwen3.6-27B
Performance
16k
tokens
595.9
PP tok/s
23.6
TG tok/s
27497
TTFT (ms)
19.8
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.3.9.dev1
macOS
macOS 26.4
Context
16,384
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 787.6 | 32.3 | 15.8 GB | view |
| 4k | 816.0 | 31.8 | 17.3 GB | view |
| 8k | 720.5 | 30.7 | 18.3 GB | view |
| 16k | 595.9 | 23.6 | 19.8 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 32.3 | 1.00× |
| 2× | 32.3 | 1.00× |
| 4× | 27.8 | 0.86× |