← Back to community benchmarks
Qwen3.5-9B-OptiQ
Performance
1k
tokens
217.1
PP tok/s
19.6
TG tok/s
4718
TTFT (ms)
6.7
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
16 GB
GPU Cores
10
Software
oMLX
v0.3.4
macOS
macOS 26.3.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 217.1 | 19.6 | 6.7 GB | current |
| 4k | 223.2 | 19.1 | 7.3 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 19.6 | 1.00× |
| 2× | 38.6 | 1.97× |
| 4× | 50.1 | 2.56× |