← Back to community benchmarks
Qwen3.5-397B-A17B
Performance
32k
tokens
429.1
PP tok/s
17.3
TG tok/s
76373
TTFT (ms)
305.5
Peak mem (GB)
Hardware
Chip
M3 Ultra (80c)
Memory
512 GB
GPU Cores
80
Software
oMLX
v0.2.7
macOS
macOS 26.3.1
Context
32,768
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 458.1 | 29.5 | 302.7 GB | view |
| 4k | 494.4 | 28.6 | 302.9 GB | view |
| 8k | 491.8 | 26.1 | 303.3 GB | view |
| 16k | 470.4 | 22.5 | 304.0 GB | view |
| 32k | 429.1 | 17.3 | 305.5 GB | current |
| 64k | 348.4 | 12.1 | 308.5 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 29.5 | 1.00× |
| 2× | 45.8 | 1.55× |
| 4× | 59.3 | 2.01× |