← Back to community benchmarks
Qwen3.5-9B
Performance
64k
tokens
205.6
PP tok/s
17.0
TG tok/s
318796
TTFT (ms)
10.8
Peak mem (GB)
Hardware
Chip
M1 Max (24c)
Memory
32 GB
GPU Cores
24
Software
oMLX
v0.2.7
macOS
macOS 26.3.1
Context
65,536
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 239.2 | 46.8 | 6.7 GB | view |
| 4k | 240.8 | 44.4 | 7.0 GB | view |
| 8k | 238.2 | 41.4 | 7.1 GB | view |
| 16k | 233.7 | 36.3 | 7.6 GB | view |
| 32k | 222.7 | 28.8 | 8.7 GB | view |
| 64k | 205.6 | 17.0 | 10.8 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 46.8 | 1.00× |
| 2× | 52.8 | 1.13× |
| 4× | 55.7 | 1.19× |