← Back to community benchmarks
Qwen3.5-9B
Performance
64k
tokens
158.5
PP tok/s
7.7
TG tok/s
413600
TTFT (ms)
10.6
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
16 GB
GPU Cores
10
Software
oMLX
v0.2.7
macOS
macOS 26.3.1
Context
65,536
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 222.3 | 19.6 | 6.5 GB | view |
| 4k | 222.8 | 18.8 | 6.8 GB | view |
| 8k | 219.3 | 17.6 | 7.0 GB | view |
| 16k | 209.9 | 15.5 | 7.5 GB | view |
| 32k | 186.1 | 12.6 | 8.5 GB | view |
| 64k | 158.5 | 7.7 | 10.6 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 19.6 | 1.00× |
| 2× | 38.6 | 1.97× |
| 4× | 48.3 | 2.46× |
| 8× | 48.9 | 2.49× |