TripoSR
A solid pick for self-hosting and full data control.
Overview
TripoSR converts a single image into a 3D mesh in one feed-forward pass, built on an LRM-style architecture trained on Objaverse renders. At 0.5B parameters it runs comfortably on laptop-class hardware, and its MIT licence means fully local, self-hosted use with data never leaving your infrastructure, regardless of Stability AI's UK base. Real limit: Stability AI itself flags this model as superseded by SF3D, which offers faster generation and more game-ready output.
Skill profile
Not disclosed
Strengths
- Open-source and self-hostable
Limitations
- API pricing not disclosed
Who is it for
- you want to control cost or self-host
- you have GDPR constraints
Ideal use cases
- Rapid 3D asset prototyping
- Single-photo object reconstruction
- Game asset draft generation
- Internal 3D modeling tools
Access & availability
Key specifications
Privacy
Run it locally
| Quantization | Disk | RAM / VRAM | Typical hardware |
|---|---|---|---|
| Q4 · recommended | 0.3 GB | 2 GB | Any recent PC/Mac |
| Q8 · balanced | 0.5 GB | 3 GB | Any recent PC/Mac |
| FP16 · max quality | 1 GB | 3 GB | Any recent PC/Mac |
Estimates for a moderate context. Long contexts need more RAM (KV cache).
Deploy
Copy-ready commands generated from this card. Adjust context length and GPU count to your hardware.
OpenAI-compatible server for production on NVIDIA GPUs.
pip install vllm
vllm serve stabilityai/TripoSR \
--max-model-len 32768 \
--tensor-parallel-size 1 \
--dtype autoAdvanced data · for expertsArchitecture, modalities, detailed cost, full benchmarks▾
| Arena Elo | — |
| MMLU | — |
| GPQA | — |
| HumanEval | — |
| SWE-Bench | — |
| MATH | — |