← Back to community benchmarks
Qwen3.5-9B
Performance
4k
tokens
209.8
PP tok/s
18.4
TG tok/s
19525
TTFT (ms)
6.8
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
32 GB
GPU Cores
10
Software
oMLX
v0.2.6
macOS
macOS 26.3
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 210.3 | 19.6 | 6.5 GB | view |
| 4k | 209.8 | 18.4 | 6.8 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 19.6 | 1.00× |
| 2× | 36.3 | 1.85× |
| 4× | 48.6 | 2.48× |