Alibaba/Qwen · open-weights model
Qwen3.5-9B
Qwen3.5-9B is a 9.7B-parameter model by Alibaba/Qwen. Its smallest quant (Q4_K_M) needs at least 7.2GB of GPU-addressable memory at 8K context; it loads cleanly at a quality quant on 46 of the 50 machines we track.
- Parameters
- 9.7B
- Layers
- 32
- Max context
- 256K
- Attention
- HYBRID
- License
- apache-2.0
Config from Qwen/Qwen3.5-9B
Quants and what they need
Measured file sizes; “needs” = weights + KV cache at 8K context + overhead.
| Quant | File size | Needs ≥ |
|---|---|---|
| Q8_0 | 9.5 GB | 11.1 GB |
| Q6_K | 7.5 GB | 9.0 GB |
| Q5_K_M | 6.6 GB | 8.1 GB |
| Q4_K_M | 5.7 GB | 7.2 GB |
What runs Qwen3.5-9B
Every machine we track, graded at its best clean-fit quant.
Verdicts computed from published specs and measured GGUF sizes — how the math works.