← Back to community benchmarks
Qwen3.5-397B-A17B
Performance
1k
tokens
389.3
PP tok/s
35.1
TG tok/s
2631
TTFT (ms)
209.6
Peak mem (GB)
Hardware
Chip
M3 Ultra (80c)
Memory
512 GB
GPU Cores
80
Software
oMLX
v0.2.6
macOS
macOS 15.7.3
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 389.3 | 35.1 | 209.6 GB | current |
| 4k | 473.9 | 33.7 | 209.9 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 35.1 | 1.00× |
| 2× | 59.8 | 1.70× |
| 4× | 87.8 | 2.50× |
| 8× | 124.9 | 3.56× |