← Back to community benchmarks
Qwen3.5-9B
Performance
4k
tokens
168.1
PP tok/s
18.0
TG tok/s
24372
TTFT (ms)
6.8
Peak mem (GB)
Hardware
Chip
M3 (10c)
Memory
16 GB
GPU Cores
10
Software
oMLX
v0.2.12
macOS
macOS 26.3.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 187.7 | 18.7 | 6.5 GB | view |
| 4k | 168.1 | 18.0 | 6.8 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 18.7 | 1.00× |
| 2× | 8.4 | 0.45× |
| 4× | 22.4 | 1.20× |