← Back to community benchmarks
Qwen3.5-9B-OptiQ
Performance
4k
tokens
34.7
PP tok/s
7.1
TG tok/s
117874
TTFT (ms)
6.9
Peak mem (GB)
Hardware
Chip
M1 (8c)
Memory
16 GB
GPU Cores
8
Software
oMLX
v0.2.8
macOS
macOS 26.3
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 34.2 | 7.3 | 6.6 GB | view |
| 4k | 34.7 | 7.1 | 6.9 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 7.3 | 1.00× |
| 2× | 7.9 | 1.08× |
| 4× | 8.3 | 1.14× |