AI tools under 8 GB of VRAM
VRAM thresholds, backends and licenses come from the tool fact sheets: every value is collected by code from an official source and stamped with the date it was checked. Requirements marked with an asterisk * are the authors’ own description, not our measurement. Details are on each tool’s page.
Showing 12 of 68
| Tool | Type | Runs | VRAM | Backends | Formats |
|---|---|---|---|---|---|
| MeshAnything | 3D | open source | from 7 GB * | CUDA | — |
| Stable Fast 3Dimage-to-3d | 3D | open source | from 6 GB * | CUDAApple MPS | glb |
| threestudio | 3D | open source | from 6 GB * | CUDA | obj |
| TripoSRimage-to-3d | 3D | open source | from 6 GB * | CUDA | — |
| Zero123++ | 3D | open source | from 5 GB * | — | — |
| ACE-Steptext-to-audio | Audio | open source | from 8 GB * | — | — |
| ChatTTStext-to-audio | Audio | open source | from 4 GB * | — | — |
| MMAudio | Audio | open source | from 6 GB * | CUDA | — |
| MOSS-SoundEffect without CUDA (Mac and AMD) | Audio | open source | from 8 GB (8–10 GB) * | Apple MPSAMD ROCm | — |
| FramePack | Video | open source | from 6 GB * | CUDA | — |
| LTX-Videoimage-to-video | Video | open source | from 1 GB * | Apple MPS | — |
| Pyramid Flowtext-to-video | Video | open source | from 8 GB * | Apple MPS | — |
Cloud services — no VRAM needed
They compute on their own servers, so a hardware filter does not apply to them.
| Luma GenieGeneration and editing of video, images, audio, and text using AI agents | 3D | cloud | cloud | not needed | JPG |
| Masterpiece XGeneration of 3D scenes and assets using AI | 3D | cloud | cloud | not needed | — |
| Meshytext-to-3D, image-to-3D, AI texturing, image generation, animation | 3D | cloud | cloud | not needed | GLB, FBX, OBJ, USDZ, STL |
| Polycam3D scanning, generation of 3D models, floor plans, reality capture | 3D | cloud | cloud | not needed | GLTF, OBJ, FBX, DAE, STL, USDZ, … |
| Rodintext-to-3D, image-to-3D, text-to-image, image-to-video, 3D avatar generation, texture generation, HDRI generation | 3D | cloud | cloud | not needed | GLB, OBJ, FBX |
| Tripo AItext-to-3D, image-to-3D, texturing, rigging, animation | 3D | cloud | cloud | not needed | JPG, PNG, WEBP |
| Dream Machinetext-to-video, image-to-video, video extension, video interpolation | Video | cloud | cloud | not needed | MP4 |
| Hailuoimage-to-video, text-to-video | Video | cloud | cloud | not needed | — |
| KlingVideo and image generation using AI | Video | cloud | cloud | not needed | — |
| PikaImage-to-Video, Video-to-Video, Text-to-Video | Video | cloud | cloud | not needed | — |
| RunwayVideo avatar generation from audio or text, avatar creation and management, real-time conversations | Video | cloud | cloud | not needed | — |
| Soratext-to-video, image-to-video, video-to-video | Video | cloud | cloud | not needed | MP4 |
| Veotext-to-video, image-to-video | Video | cloud | cloud | not needed | video/mp4 |
| ViduVideo generation: text-to-video, image-to-video, reference-to-video, start-end-to-video, upscale | Video | cloud | cloud | not needed | png, jpeg, jpg, webp |
Requirements not stated by the authors
The official sources for these tools have no data for the selected filter — that means “unknown”, not “won’t work”.
| 3DTopia | 3D | open source | not stated | CUDA | glb |
| CRM | 3D | open source | not stated | — | obj |
| DreamGaussian | 3D | open source | not stated | — | — |
| Era3D | 3D | open source | not stated | — | — |
| Hunyuan3D 2.1 without CUDA (Mac and AMD) | 3D | open source | not stated | Apple MPSAMD ROCm | obj, glb, ply, stl, fbx, dae, 3mf |
| InstantMeshimage-to-3d | 3D | open source | not stated | CUDA | obj |
| LGMtext-to-3d | 3D | open source | not stated | — | — |
| Michelangelo | 3D | open source | not stated | — | — |
| MVDream | 3D | open source | not stated | — | — |
| Nerfstudio | 3D | open source | not stated | CUDA | — |
| One-2-3-45 | 3D | open source | not stated | — | — |
| OpenLRMimage-to-3d | 3D | open source | not stated | CUDA | obj |
| Point-E | 3D | open source | not stated | — | — |
| Shap-E | 3D | open source | not stated | — | — |
| TRELLISimage-to-3d | 3D | open source | not stated | CUDA | glb |
| Unique3D | 3D | open source | not stated | CUDA | — |
| Wonder3D | 3D | open source | not stated | — | — |
| CosyVoicetext-to-speech | Audio | open source | not stated | — | — |
| DiffRhythm | Audio | open source | not stated | — | — |
| F5-TTStext-to-speech | Audio | open source | not stated | AMD ROCm | — |
| Fish Speechtext-to-speech | Audio | open source | not stated | CUDA | — |
| MOSS-SoundEffecttext-to-audio | Audio | open source | not stated | — | — |
| MusicGentext-to-audio | Audio | open source | not stated | — | — |
| OpenVoicetext-to-speech | Audio | open source | not stated | — | — |
| Stable Audio Opentext-to-audio | Audio | open source | not stated | — | — |
| XTTStext-to-speech | Audio | open source | not stated | CUDA | — |
| YuEtext-generation | Audio | open source | not stated | — | — |
| CogVideoXtext-to-video | Video | open source | not stated | CUDA | — |
| Latte | Video | open source | not stated | CUDA | — |
| Open-Sora | Video | open source | not stated | — | — |
| Stable Video Diffusionimage-to-video | Video | open source | not stated | — | — |
| VideoCrafter | Video | open source | not stated | — | — |
Fact sheets are re-checked monthly; every value on a tool page has a source link and a check date. The asterisk * means “as described by the author”: a developer’s statement, not an independent measurement.