← Back to community benchmarks
Qwen3.5-9B
Performance
1k
tokens
227.9
PP tok/s
37.4
TG tok/s
4494
TTFT (ms)
6.7
Peak mem (GB)
Hardware
Chip
M1 Max (24c)
Memory
32 GB
GPU Cores
24
Software
oMLX
v0.2.6
macOS
macOS 15.6.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 227.9 | 37.4 | 6.7 GB | current |
| 4k | 185.8 | 29.9 | 7.0 GB | view |
| 8k | 186.8 | 29.2 | 7.1 GB | view |
| 16k | 177.4 | 26.7 | 7.6 GB | view |
| 32k | 163.8 | 20.1 | 8.7 GB | view |
| 64k | 154.9 | 14.4 | 10.8 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 37.4 | 1.00× |
| 2× | 27.1 | 0.72× |
| 4× | 43.4 | 1.16× |