What Can the NVIDIA RTX 3090 Ti Run?
24 GB · compatibility with 168 AI models
Home › GPUs › NVIDIA RTX 3090 Ti
Short answer: the NVIDIA RTX 3090 Ti (24 GB) can run 166 of 168 AI image, video, 3D and audio models we track. Best picks: MiniMax H3 FL2VA, MiniMax H3 Ref2VA, Qwen-Image 2.1, Z-Image Turbo, WAN 2.2 T2V A14B (MoE).
| Perfect | Great | Good | Usable | Barely | Can't Run |
|---|---|---|---|---|---|
| 13 models | 126 models | 27 models | 0 models | 0 models | 2 models |
NVIDIA RTX 3090 Ti specs for AI
| Brand | NVIDIA |
|---|---|
| Series | RTX 30 |
| VRAM | 24 GB |
| Architecture | ampere |
| FP16 compute | 40 TFLOPS |
| Memory bandwidth | 1008 GB/s |
| FP8 support | No |
| Released | 2022 |
| Launch price | $1499 |
AI models on the NVIDIA RTX 3090 Ti
Each model uses the best format that fits in 24 GB. How ratings work.
Text to Image
| Model | Rating | Runs as | VRAM used | Speed |
|---|---|---|---|---|
| Stable Diffusion 1.5 | Great | FP16 | 4 GB | Fast |
| Stable Diffusion 1.4 | Great | FP16 | 4 GB | Fast |
| Stable Diffusion 2.1 | Great | FP16 | 5 GB | Fast |
| PixArt-Alpha 600M | Great | FP16 | 6 GB | Fast |
| Stable Diffusion 2.0 | Great | FP16 | 5 GB | Fast |
| SDXL Base 1.0 | Great | FP16 | 7 GB | Fast |
| SDXL Turbo | Great | FP16 | 7 GB | Fast |
| Stable Diffusion 3.5 Medium (2.5B) | Great | FP16 | 8 GB | Fast |
| Animagine XL 3.1 | Great | FP16 | 7 GB | Fast |
| Pony Diffusion v6 XL | Great | FP16 | 7 GB | Fast |
| NoobAI XL | Great | FP16 | 7 GB | Fast |
| Juggernaut XL Ragnarok | Great | FP16 | 7 GB | Fast |
| SDXL Lightning 4-step | Great | FP16 | 7 GB | Fast |
| DreamShaper XL | Great | FP16 | 7 GB | Fast |
| Illustrious XL v1.0 | Great | FP16 | 7 GB | Fast |
| Playground v2.5 2.6B | Great | FP16 | 7 GB | Fast |
| RealVisXL v5.0 | Great | FP16 | 7 GB | Fast |
| Epicrealism XL | Great | FP16 | 7 GB | Fast |
| PixArt-Sigma 900M | Great | FP16 | 7 GB | Fast |
| Stable Diffusion 3 Medium (2B) | Great | FP16 | 7 GB | Fast |
| SDXL Hyper 1-step | Great | FP16 | 7 GB | Fast |
| HunyuanDiT 1.5B | Great | FP16 | 8 GB | Fast |
| Z-Image Turbo | Great | FP16 | 10 GB | Fast |
| MOSS-Image 5B | Great | FP16 | 12 GB | Fast |
| Flux.1 Lite | Great | FP16 | 12 GB | Fast |
| AuraFlow 0.3 | Great | FP16 | 12 GB | Fast |
| Flux.2 Klein 4B | Great | FP16 | 13 GB | Fast |
| Qwen-Image 2.1 | Great | FP16 | 14 GB | Fast |
| Z-Image Base | Great | FP16 | 14 GB | Fast |
| Ming-Image 0.1 Design | Great | FP16 | 14 GB | Fast |
| Kolors | Great | FP16 | 14 GB | Fast |
| Krea 2 Turbo | Great | GGUF Q4 | 8 GB | Moderate |
| ERNIE-Image 8B | Great | FP16 | 16 GB | Fast |
| HiDream-O1-Image 8.8B | Great | FP16 | 16 GB | Fast |
| Seedream 3.0 | Great | FP16 | 16 GB | Fast |
| GLM-Image | Great | FP16 | 16 GB | Fast |
| FLUX.2 Klein 9B | Great | FP16 | 18 GB | Fast |
| Stable Diffusion 3.5 Large (8B) | Great | FP16 | 18 GB | Fast |
| Stable Diffusion 3.5 Large Turbo | Great | FP16 | 18 GB | Fast |
| Chroma1 HD | Great | FP16 | 18 GB | Fast |
| Qwen-Image 2512 (20B) | Good | GGUF Q4 | 12 GB | Moderate |
| Ideogram 4.0 | Good | FP16 | 19 GB | Fast |
| HunyuanImage 3.0 | Good | FP16 | 20 GB | Fast |
| Flux.2 Dev 32B | Good | GGUF Q4 | 18 GB | Moderate |
| Flux.1 Dev 12B | Good | FP16 | 24 GB | Fast |
| Flux.1 Schnell 12B | Good | FP16 | 24 GB | Fast |
| FLUX.1 Krea Dev | Good | FP16 | 24 GB | Fast |
Image to Image
| Model | Rating | Runs as | VRAM used | Speed |
|---|---|---|---|---|
| SD 1.5 img2img | Great | FP16 | 4 GB | Fast |
| InstructPix2Pix | Great | FP16 | 5 GB | Fast |
| SDXL img2img | Great | FP16 | 7 GB | Fast |
| IP-Adapter SDXL | Great | FP16 | 9 GB | Fast |
| IP-Adapter FaceID SDXL | Great | FP16 | 10 GB | Fast |
| Mage-Flow 4B | Great | FP16 | 10 GB | Fast |
| LongCat-Image Edit | Great | FP16 | 15 GB | Fast |
| Qwen-Image-Edit 2511 | Good | GGUF Q4 | 12 GB | Moderate |
| Boogu-Image Edit | Good | FP16 | 21 GB | Fast |
| Flux.1 Dev img2img 12B | Good | FP16 | 24 GB | Fast |
| Flux Kontext Dev | Good | FP16 | 24 GB | Fast |
Inpainting
| Model | Rating | Runs as | VRAM used | Speed |
|---|---|---|---|---|
| SD 1.5 Inpainting | Great | FP16 | 4 GB | Fast |
| SDXL Inpainting | Great | FP16 | 7 GB | Fast |
| BrushNet | Great | FP16 | 8 GB | Fast |
| PowerPaint v2.1 | Great | FP16 | 7 GB | Fast |
| Flux.1 Fill Dev | Good | FP16 | 24 GB | Fast |
ControlNet
| Model | Rating | Runs as | VRAM used | Speed |
|---|---|---|---|---|
| ControlNet SD 1.5 | Great | FP16 | 5 GB | Fast |
| T2I-Adapter SDXL | Great | FP16 | 8 GB | Fast |
| ControlNet SDXL | Great | FP16 | 9 GB | Fast |
| ControlNet Flux | Great | GGUF Q4 | 10 GB | Moderate |
Video
| Model | Rating | Runs as | VRAM used | Speed |
|---|---|---|---|---|
| WAN 2.1 T2V 1.3B | Great | FP16 | 6 GB | Fast |
| AnimateDiff Lightning | Great | FP16 | 6 GB | Fast |
| AnimateDiff v3 (SD 1.5) | Great | FP16 | 6 GB | Fast |
| ZeroScope v2 576w | Great | FP16 | 6 GB | Fast |
| AnimateDiff V2V | Great | FP16 | 6 GB | Fast |
| AnimateDiff I2V | Great | FP16 | 6 GB | Fast |
| Stable Video Diffusion 1.1 | Great | FP16 | 8 GB | Fast |
| CogVideoX 2B | Great | FP16 | 8 GB | Fast |
| ModelScope T2V | Great | FP16 | 8 GB | Fast |
| TokenFlow | Great | FP16 | 8 GB | Fast |
| Latte | Great | FP16 | 8 GB | Fast |
| SEINE | Great | FP16 | 8 GB | Fast |
| Kandinsky 6.0 Video Lite 3B | Great | FP16 | 9 GB | Fast |
| LTX-Video 0.9 (2B) | Great | FP16 | 10 GB | Fast |
| LTX-Video I2V | Great | FP16 | 10 GB | Fast |
| Stable Video Diffusion XT 1.1 (25 frames) | Great | FP16 | 10 GB | Fast |
| DynamiCrafter 512 | Great | FP16 | 10 GB | Fast |
| WAN 2.2 TI2V 5B | Great | FP16 | 12 GB | Fast |
| AnimateDiff SDXL | Great | FP16 | 12 GB | Fast |
| Waver 1.0 | Great | FP16 | 12 GB | Fast |
| CogVideoX 5B | Great | FP16 | 14 GB | Fast |
| CogVideoX 5B I2V | Great | FP16 | 14 GB | Fast |
| SkyReels V1 | Great | FP16 | 14 GB | Fast |
| SkyReels V1 I2V | Great | FP16 | 14 GB | Fast |
| WAN 2.2 T2V A14B (MoE) | Great | GGUF Q4 | 8 GB | Moderate |
| WAN 2.2 I2V A14B | Great | GGUF Q4 | 8 GB | Moderate |
| WAN 2.1 T2V 14B | Great | GGUF Q4 | 8 GB | Moderate |
| WAN 2.1 I2V 480P 14B | Great | GGUF Q4 | 8 GB | Moderate |
| WAN 2.1 V2V | Great | GGUF Q4 | 8 GB | Moderate |
| HunyuanVideo T2V v1.5 | Great | GGUF Q4 | 8 GB | Moderate |
| HunyuanVideo I2V v1.5 | Great | GGUF Q4 | 8 GB | Moderate |
| HunyuanVideo 13B T2V | Great | GGUF Q4 | 8 GB | Moderate |
| HunyuanVideo I2V | Great | GGUF Q4 | 8 GB | Moderate |
| SkyReels V3 R2V 14B | Great | GGUF Q4 | 9 GB | Moderate |
| Wan 2.2 Animate 14B | Great | GGUF Q4 | 11 GB | Moderate |
| Wan 2.2 S2V 14B | Great | GGUF Q4 | 10 GB | Moderate |
| WAN 2.1 I2V 720P 14B | Great | GGUF Q4 | 10 GB | Moderate |
| LTX-2 19B | Great | GGUF Q4 | 11 GB | Moderate |
| Wan-Animate-2 14B | Great | GGUF Q4 | 10 GB | Moderate |
| SCAIL-2 14B | Great | GGUF Q4 | 10 GB | Moderate |
| Wan-Dancer 14B | Great | GGUF Q4 | 10 GB | Moderate |
| HuMo 17B | Great | GGUF Q4 | 10 GB | Moderate |
| DynamiCrafter 1024 | Great | FP16 | 18 GB | Fast |
| MiniMax H3 FL2VA | Good | GGUF Q4 | 12 GB | Moderate |
| MiniMax H3 Ref2VA | Good | GGUF Q4 | 12 GB | Moderate |
| LTX-2.5 22B | Good | GGUF Q4 | 13 GB | Moderate |
| LTX-2.3 22B | Good | GGUF Q4 | 13 GB | Moderate |
| LongCat-Video 13.6B | Good | Offload | 6 GB | Slow |
| FramePack I2V HY FP8 | Good | Offload | 8 GB | Very Slow |
| Ovi 1.1 | Good | FP16 | 23 GB | Fast |
| LTX-Video 13B | Good | Offload | 12 GB | Very Slow |
| Mochi 1 10B | Good | Offload | 16 GB | Very Slow |
| Open-Sora 2.0 (11B) | Good | FP16 | 24 GB | Fast |
| MAGI-1 | Good | FP16 | 24 GB | Fast |
| MOVA | Can't Run | — | needs 29 GB | — |
Upscaler
| Model | Rating | Runs as | VRAM used | Speed |
|---|---|---|---|---|
| 4x-UltraSharp | Perfect | FP32 | 0.3 GB | Fast |
| 4x-Remacri | Perfect | FP32 | 0.3 GB | Fast |
| SwinIR | Perfect | FP32 | 0.5 GB | Fast |
| RealESRGAN x4plus | Perfect | FP32 | 0.3 GB | Fast |
| HAT | Perfect | FP32 | 0.5 GB | Fast |
| DAT | Perfect | FP32 | 0.5 GB | Fast |
| ScuNET | Perfect | FP32 | 0.3 GB | Fast |
| LDSR | Great | FP16 | 4 GB | Fast |
| SeedVR2 3B | Great | FP16 | 9 GB | Fast |
| SeedVR2 7B | Great | FP16 | 16 GB | Fast |
Face/Restore
| Model | Rating | Runs as | VRAM used | Speed |
|---|---|---|---|---|
| GFPGAN v1.4 | Perfect | FP32 | 0.3 GB | Fast |
| CodeFormer v0.1 | Perfect | FP32 | 0.3 GB | Fast |
VAE
| Model | Rating | Runs as | VRAM used | Speed |
|---|---|---|---|---|
| SD 1.5 VAE ft-mse | Perfect | FP32 | 0.2 GB | Fast |
| Flux VAE | Perfect | FP32 | 0.3 GB | Fast |
| SDXL VAE | Perfect | FP32 | 0.3 GB | Fast |
| TAESD / TAESDXL | Perfect | FP32 | 0.1 GB | Fast |
3D
| Model | Rating | Runs as | VRAM used | Speed |
|---|---|---|---|---|
| TripoSR | Great | FP16 | 4 GB | Fast |
| Shap-E | Great | FP16 | 4 GB | Fast |
| InstantMesh | Great | FP16 | 6 GB | Fast |
| Zero123++ v1.2 | Great | FP16 | 6 GB | Fast |
| LGM | Great | FP16 | 8 GB | Fast |
| One-2-3-45 | Great | FP16 | 8 GB | Fast |
| Hunyuan3D 2.1 | Great | FP16 | 10 GB | Fast |
| SV3D | Great | FP16 | 10 GB | Fast |
| Hunyuan3D 2.0 | Great | FP16 | 12 GB | Fast |
| Pixal3D | Great | FP16 | 14 GB | Fast |
| TRELLIS.2 4B | Good | FP16 | 24 GB | Fast |
| SAM 3D Objects | Can't Run | — | needs 32 GB | — |
Audio
| Model | Rating | Runs as | VRAM used | Speed |
|---|---|---|---|---|
| MusicGen Small (300M) | Great | FP16 | 2 GB | Fast |
| XTTS v2 | Great | FP16 | 3 GB | Fast |
| Stable Audio 3 Small-SFX | Great | FP16 | 3 GB | Fast |
| Whisper Large v3 | Great | FP16 | 4 GB | Fast |
| Chatterbox Multilingual | Great | FP16 | 4 GB | Fast |
| MMAudio Large 44k | Great | FP16 | 4 GB | Fast |
| Stable Audio Open | Great | FP16 | 4 GB | Fast |
| Qwen3-TTS 1.7B | Great | FP16 | 5 GB | Fast |
| MusicGen Medium (1.5B) | Great | FP16 | 6 GB | Fast |
| IndexTTS 2.5 | Great | FP16 | 6 GB | Fast |
| ACE-Step 1.5 Turbo | Great | FP16 | 8 GB | Fast |
| VibeVoice 1.5B | Great | FP16 | 7 GB | Fast |
| Bark | Great | FP16 | 8 GB | Fast |
| Stable Audio 3 Medium | Great | FP16 | 7 GB | Fast |
| MusicGen Large (3.3B) | Great | FP16 | 12 GB | Fast |
| YuE2 3B | Good | FP16 | 24 GB | Fast |
| MiniMax Music 3 | Good | FP16 | 24 GB | Fast |
| Fish Audio S2 Pro 4B | Good | FP16 | 24 GB | Fast |
Frequently asked questions
How much VRAM does the NVIDIA RTX 3090 Ti have?
The NVIDIA RTX 3090 Ti has 24 GB of VRAM with 1008 GB/s of memory bandwidth.
What AI models can the NVIDIA RTX 3090 Ti run?
It can run 166 of the 168 AI models we track: 13 perfectly (S), 126 great (A), 27 good (B), 0 usable (C) and 0 barely (D). 2 need more VRAM than it has.
Can the NVIDIA RTX 3090 Ti run MiniMax H3 FL2VA?
Yes, in GGUF Q4 (rating B, good).
Can the NVIDIA RTX 3090 Ti run MiniMax H3 Ref2VA?
Yes, in GGUF Q4 (rating B, good).
Can the NVIDIA RTX 3090 Ti run Qwen-Image 2.1?
Yes, in FP16 (rating A, great).
Can the NVIDIA RTX 3090 Ti run Z-Image Turbo?
Yes, in FP16 (rating A, great).