← Back to community benchmarks
Qwen3.5-9B
Performance
8k
tokens
158.0
PP tok/s
28.5
TG tok/s
51857
TTFT (ms)
7.1
Peak mem (GB)
Hardware
Chip
M1 Pro (16c)
Memory
32 GB
GPU Cores
16
Software
oMLX
v0.2.7
macOS
macOS 26.3.1
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 159.1 | 32.1 | 6.7 GB | view |
| 4k | 159.6 | 31.0 | 7.0 GB | view |
| 8k | 158.0 | 28.5 | 7.1 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 32.1 | 1.00× |
| 2× | 36.6 | 1.14× |
| 4× | 38.4 | 1.20× |