← Back to community benchmarks
Qwen3.5-9B-OptiQ
Performance
1k
tokens
170.1
PP tok/s
22.5
TG tok/s
6019
TTFT (ms)
7.8
Peak mem (GB)
Hardware
Chip
M1 Pro (14c)
Memory
16 GB
GPU Cores
14
Software
oMLX
v0.2.6
macOS
macOS 15.7.4
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 170.1 | 22.5 | 7.8 GB | current |
| 4k | 180.3 | 21.4 | 8.2 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 22.5 | 1.00× |
| 2× | 32.0 | 1.42× |
| 4× | 36.3 | 1.61× |