← Back to community benchmarks
Qwen3.5-9B
Performance
32k
tokens
149.0
PP tok/s
20.6
TG tok/s
219949
TTFT (ms)
8.7
Peak mem (GB)
Hardware
Chip
M1 Pro (16c)
Memory
16 GB
GPU Cores
16
Software
oMLX
v0.2.6
macOS
macOS 26.3.1
Context
32,768
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 160.2 | 33.1 | 6.7 GB | view |
| 4k | 160.9 | 31.5 | 7.0 GB | view |
| 8k | 159.3 | 29.0 | 7.1 GB | view |
| 16k | 155.6 | 25.2 | 7.6 GB | view |
| 32k | 149.0 | 20.6 | 8.7 GB | current |
| 64k | 135.3 | 14.2 | 10.8 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 33.1 | 1.00× |
| 2× | 36.8 | 1.11× |
| 4× | 37.6 | 1.14× |
| 8× | 31.1 | 0.94× |