← Back to community benchmarks
Qwen3.5-9B
Performance
4k
tokens
134.7
PP tok/s
27.7
TG tok/s
30404
TTFT (ms)
7.0
Peak mem (GB)
Hardware
Chip
M1 Pro (14c)
Memory
16 GB
GPU Cores
14
Software
oMLX
v0.2.6
macOS
macOS 15.7.3
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 130.0 | 29.3 | 6.7 GB | view |
| 4k | 134.7 | 27.7 | 7.0 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 29.3 | 1.00× |
| 2× | 32.5 | 1.11× |
| 4× | 32.1 | 1.10× |