← Back to community benchmarks
Qwen3.5-397B-A17B
Performance
4k
tokens
513.2
PP tok/s
33.8
TG tok/s
7982
TTFT (ms)
210.7
Peak mem (GB)
Hardware
Chip
M3 Ultra (80c)
Memory
512 GB
GPU Cores
80
Software
oMLX
v0.2.9
macOS
macOS 26.3
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 448.8 | 35.1 | 210.4 GB | view |
| 4k | 513.2 | 33.8 | 210.7 GB | current |
| 8k | 517.2 | 31.7 | 211.0 GB | view |
| 16k | 495.3 | 28.9 | 211.8 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 35.1 | 1.00× |
| 2× | 55.8 | 1.59× |
| 4× | 81.4 | 2.32× |