← Back to community benchmarks
Qwen3.5-9B
Performance
64k
tokens
1,139
PP tok/s
29.4
TG tok/s
57521
TTFT (ms)
10.8
Peak mem (GB)
Hardware
Chip
M3 Ultra (80c)
Memory
512 GB
GPU Cores
80
Software
oMLX
v0.2.6
macOS
macOS 26.2
Context
65,536
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,465 | 105.7 | 6.7 GB | view |
| 4k | 1,485 | 101.0 | 7.0 GB | view |
| 8k | 1,465 | 96.2 | 7.1 GB | view |
| 16k | 1,413 | 75.6 | 7.6 GB | view |
| 32k | 1,315 | 50.1 | 8.7 GB | view |
| 64k | 1,139 | 29.4 | 10.8 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 105.7 | 1.00× |
| 2× | 181.9 | 1.72× |
| 4× | 246.1 | 2.33× |