← Back to community benchmarks
Qwen3.5-9B
Performance
4k
tokens
185.7
PP tok/s
18.3
TG tok/s
22054
TTFT (ms)
6.3
Peak mem (GB)
Hardware
Chip
M3 (10c)
Memory
16 GB
GPU Cores
10
Software
oMLX
v0.3.4
macOS
macOS 15.7.3
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 179.9 | 19.1 | 5.7 GB | view |
| 4k | 185.7 | 18.3 | 6.3 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 19.1 | 1.00× |
| 2× | 36.7 | 1.92× |
| 4× | 42.1 | 2.20× |