← Back to community benchmarks
Qwen3.5-9B
Performance
4k
tokens
157.4
PP tok/s
31.1
TG tok/s
26018
TTFT (ms)
7.0
Peak mem (GB)
Hardware
Chip
M1 Pro (16c)
Memory
32 GB
GPU Cores
16
Software
oMLX
v0.2.6
macOS
macOS 15.7.4
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 156.2 | 32.6 | 6.7 GB | view |
| 4k | 157.4 | 31.1 | 7.0 GB | current |
| 8k | 155.7 | 29.1 | 7.1 GB | view |
| 16k | 150.4 | 25.7 | 7.6 GB | view |
| 32k | 147.1 | 21.9 | 8.7 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 32.6 | 1.00× |
| 2× | 36.6 | 1.12× |
| 4× | 38.5 | 1.18× |
| 8× | 30.7 | 0.94× |