← Back to community benchmarks
Qwen3.5-9B
Performance
4k
tokens
225.7
PP tok/s
20.5
TG tok/s
18149
TTFT (ms)
6.8
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
16 GB
GPU Cores
10
Software
oMLX
v0.2.7
macOS
macOS 26.3.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 225.4 | 21.0 | 6.5 GB | view |
| 4k | 225.7 | 20.5 | 6.8 GB | current |
| 8k | 217.6 | 18.6 | 7.0 GB | view |
| 16k | 203.0 | 15.3 | 7.5 GB | view |
| 32k | 186.7 | 15.4 | 8.5 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 21.0 | 1.00× |
| 2× | 42.1 | 2.00× |
| 4× | 50.4 | 2.40× |
| 8× | 51.9 | 2.47× |