← Back to community benchmarks
Qwen3.5-9B
Performance
1k
tokens
221.0
PP tok/s
20.5
TG tok/s
4633
TTFT (ms)
6.5
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
32 GB
GPU Cores
10
Software
oMLX
v0.2.10
macOS
macOS 26.3.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 221.0 | 20.5 | 6.5 GB | current |
| 4k | 221.0 | 19.3 | 6.8 GB | view |
| 8k | 220.6 | 13.5 | 7.0 GB | view |
| 16k | 212.8 | 17.8 | 8.1 GB | view |
| 64k | 159.0 | 11.3 | 10.6 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 20.5 | 1.00× |
| 2× | 39.2 | 1.91× |
| 4× | 51.7 | 2.52× |
| 8× | 53.6 | 2.61× |