← Back to community benchmarks
Qwen3.5-9B
Performance
32k
tokens
1,272
PP tok/s
39.6
TG tok/s
25754
TTFT (ms)
8.7
Peak mem (GB)
Hardware
Chip
M3 Ultra (80c)
Memory
512 GB
GPU Cores
80
Software
oMLX
v0.2.8
macOS
macOS 15.6
Context
32,768
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,359 | 57.0 | 6.7 GB | view |
| 4k | 1,406 | 52.7 | 6.8 GB | view |
| 8k | 1,406 | 55.2 | 7.1 GB | view |
| 16k | 1,368 | 55.8 | 7.6 GB | view |
| 32k | 1,272 | 39.6 | 8.7 GB | current |
| 64k | 1,085 | 27.5 | 10.8 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 57.0 | 1.00× |
| 2× | 113.8 | 2.00× |
| 4× | 220.3 | 3.86× |
| 8× | 292.2 | 5.13× |