Qwen3.5-9B-4bit
A modified 4-bit build of Qwen/Qwen3.5-9B, packaged for use inside Fluid Intelligence.
It is not fine-tuned. It may not work with other tools or for general use.
Includes the z-lab/Qwen3.5-9B-DFlash drafter.
Licensed under Apache-2.0, matching the upstream models.
- Downloads last month
- 323
Inference Providers NEW
This model isn't deployed by any Inference Provider. 馃檵 Ask for provider support