← Back to community benchmarks
Qwen3.5-9B
Performance
16k
tokens
147.3
PP tok/s
14.2
TG tok/s
111261
TTFT (ms)
7.6
Peak mem (GB)
Hardware
Chip
M1 Pro (16c)
Memory
16 GB
GPU Cores
16
Software
oMLX
v0.2.7
macOS
macOS 15.6
Context
16,384
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 157.0 | 32.3 | 6.7 GB | view |
| 4k | 156.9 | 30.6 | 7.0 GB | view |
| 8k | 154.9 | 27.5 | 7.1 GB | view |
| 16k | 147.3 | 14.2 | 7.6 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 32.3 | 1.00× |
| 2× | 36.4 | 1.13× |
| 4× | 33.1 | 1.02× |
| 8× | 31.3 | 0.97× |