← Back to community benchmarks
Qwen3.5-9B
Performance
1k
tokens
179.6
PP tok/s
18.6
TG tok/s
5700
TTFT (ms)
6.5
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
24 GB
GPU Cores
10
Software
oMLX
v0.2.6
macOS
macOS 26.3.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 179.6 | 18.6 | 6.5 GB | current |
| 4k | 171.3 | 18.0 | 6.8 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 18.6 | 1.00× |
| 2× | 34.0 | 1.83× |
| 4× | 39.9 | 2.15× |