← Back to community benchmarks
Qwen9B-Real
Performance
4k
tokens
270.7
PP tok/s
25.4
TG tok/s
15133
TTFT (ms)
6.6
Peak mem (GB)
Hardware
Chip
M3 Pro (14c)
Memory
18 GB
GPU Cores
14
Software
oMLX
v0.2.19
macOS
macOS 26.4.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 253.3 | 26.7 | 5.8 GB | view |
| 4k | 270.7 | 25.4 | 6.6 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 26.7 | 1.00× |
| 2× | 51.3 | 1.92× |
| 4× | 63.5 | 2.38× |