VoxelModel-v1: new open-source text-to-3d model on HuggingFace

On HuggingFace, the model bench-labs/VoxelModel-v1 has been published, solving the text-to-3d task. The model appeared on July 26, 2026, and the code has been released as open source. The developer does not specify VRAM requirements, export formats, licenses, or other technical details.

What it means

VoxelModel-v1 is a 3D generator based on a text description. Among the tools in our reference, there are currently no direct analogs for the text-to-3d task with open source. The closest generators from the AI 3D section — OpenLRM, Hunyuan3D 2.1, and TRELLIS — work on the image-to-3d task, meaning they require an image as input rather than text. Hunyuan3D 2.1 mentions text-to-3d in its repository tags, but the primary task is still image-to-3d. Since the developer of VoxelModel-v1 does not disclose technical specifications, it is not yet possible to compare the new model with the listed tools in terms of VRAM, model weights sizes, or export formats. The model has just appeared, and there is little detail about its capabilities. If the text-to-3d task is relevant to you, it is worth keeping an eye on updates — perhaps examples of its work and technical documentation will soon be released.