← Back to community benchmarks
Qwen3.5-9B
Performance
1k
tokens
222.6
PP tok/s
18.0
TG tok/s
4600
TTFT (ms)
6.5
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
32 GB
GPU Cores
10
Software
oMLX
v0.2.7
macOS
macOS 26.3.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 222.6 | 18.0 | 6.5 GB | current |
| 8k | 213.9 | 17.2 | 7.7 GB | view |
| 32k | 187.3 | 14.4 | 9.9 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 18.0 | 1.00× |
| 2× | 38.8 | 2.16× |
| 4× | 53.3 | 2.96× |