← Back to community benchmarks
community:Qwen3.5-9B-OptiQ
Performance
4k
tokens
222.4
PP tok/s
19.1
TG tok/s
18419
TTFT (ms)
6.9
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
32 GB
GPU Cores
10
Software
oMLX
v0.2.7
macOS
macOS 26.3.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 213.3 | 19.3 | 6.6 GB | view |
| 4k | 222.4 | 19.1 | 6.9 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 19.3 | 1.00× |
| 2× | 38.5 | 1.99× |
| 4× | 51.2 | 2.65× |
| 8× | 51.2 | 2.65× |