← Back to community benchmarks
Qwen3.5-9B
Performance
1k
tokens
185.7
PP tok/s
18.3
TG tok/s
5515
TTFT (ms)
6.5
Peak mem (GB)
Hardware
Chip
M3 (10c)
Memory
16 GB
GPU Cores
10
Software
oMLX
v0.2.6
macOS
macOS 26.3
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 185.7 | 18.3 | 6.5 GB | current |
| 4k | 180.3 | 17.7 | 6.8 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 18.3 | 1.00× |
| 2× | 22.9 | 1.25× |
| 4× | 21.9 | 1.20× |