← Back to community benchmarks
Qwen3.5-397B-A17B4.1bit
Performance
1k
tokens
401.7
PP tok/s
34.9
TG tok/s
2550
TTFT (ms)
191.6
Peak mem (GB)
Hardware
Chip
M3 Ultra (80c)
Memory
512 GB
GPU Cores
80
Software
oMLX
v0.2.7
macOS
macOS 26.3
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 401.7 | 34.9 | 191.6 GB | current |
| 4k | 477.1 | 36.3 | 191.8 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 34.9 | 1.00× |
| 2× | 36.7 | 1.05× |
| 4× | 63.7 | 1.83× |