← Back to community benchmarks
Qwen3.5-9B-OptiQ
Performance
1k
tokens
185.4
PP tok/s
13.7
TG tok/s
5524
TTFT (ms)
7.6
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
32 GB
GPU Cores
10
Software
oMLX
v0.2.6
macOS
macOS 26.3.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 185.4 | 13.7 | 7.6 GB | current |
| 4k | 197.2 | 13.0 | 8.1 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 13.7 | 1.00× |
| 2× | 26.8 | 1.96× |
| 4× | 40.7 | 2.97× |