What Can the NVIDIA RTX 4060 Ti 8GB Run?
8 GB · compatibility with 168 AI models
Home › GPUs › NVIDIA RTX 4060 Ti 8GB
Short answer: the NVIDIA RTX 4060 Ti 8GB (8 GB) can run 157 of 168 AI image, video, 3D and audio models we track. Best picks: Qwen-Image 2.1, Z-Image Turbo, WAN 2.2 TI2V 5B, SDXL Base 1.0, SDXL img2img.
| Perfect | Great | Good | Usable | Barely | Can't Run |
|---|---|---|---|---|---|
| 13 models | 1 models | 68 models | 58 models | 17 models | 11 models |
NVIDIA RTX 4060 Ti 8GB specs for AI
| Brand | NVIDIA |
|---|---|
| Series | RTX 40 |
| VRAM | 8 GB |
| Architecture | ada |
| FP16 compute | 22.1 TFLOPS |
| Memory bandwidth | 288 GB/s |
| FP8 support | Yes |
| Released | 2023 |
| Launch price | $399 |
AI models on the NVIDIA RTX 4060 Ti 8GB
Each model uses the best format that fits in 8 GB. How ratings work.
Text to Image
| Model | Rating | Runs as | VRAM used | Speed |
|---|---|---|---|---|
| Stable Diffusion 1.5 | Good | FP16 | 4 GB | Fast |
| Stable Diffusion 1.4 | Good | FP16 | 4 GB | Fast |
| Stable Diffusion 2.1 | Good | FP16 | 5 GB | Moderate |
| Stable Diffusion 2.0 | Good | FP16 | 5 GB | Moderate |
| PixArt-Alpha 600M | Good | FP16 | 6 GB | Moderate |
| Z-Image Turbo | Good | FP8 | 6 GB | Moderate |
| FLUX.2 Klein 9B | Good | GGUF Q4 | 5 GB | Slow |
| ERNIE-Image 8B | Good | GGUF Q4 | 5 GB | Slow |
| Chroma1 HD | Good | GGUF Q4 | 5 GB | Slow |
| SDXL Base 1.0 | Good | FP16 | 7 GB | Moderate |
| SDXL Turbo | Good | FP16 | 7 GB | Moderate |
| Animagine XL 3.1 | Good | FP16 | 7 GB | Moderate |
| Pony Diffusion v6 XL | Good | FP16 | 7 GB | Moderate |
| NoobAI XL | Good | FP16 | 7 GB | Moderate |
| Juggernaut XL Ragnarok | Good | FP16 | 7 GB | Moderate |
| SDXL Lightning 4-step | Good | FP16 | 7 GB | Moderate |
| DreamShaper XL | Good | FP16 | 7 GB | Moderate |
| Illustrious XL v1.0 | Good | FP16 | 7 GB | Moderate |
| Playground v2.5 2.6B | Good | FP16 | 7 GB | Moderate |
| RealVisXL v5.0 | Good | FP16 | 7 GB | Moderate |
| Epicrealism XL | Good | FP16 | 7 GB | Moderate |
| PixArt-Sigma 900M | Good | FP16 | 7 GB | Moderate |
| Stable Diffusion 3 Medium (2B) | Good | FP16 | 7 GB | Moderate |
| SDXL Hyper 1-step | Good | FP16 | 7 GB | Moderate |
| Qwen-Image 2.1 | Good | FP8 | 7 GB | Moderate |
| MOSS-Image 5B | Good | FP8 | 7 GB | Moderate |
| Ideogram 4.0 | Good | GGUF Q4 | 6 GB | Slow |
| Ming-Image 0.1 Design | Good | GGUF Q4 | 6 GB | Slow |
| Flux.1 Lite | Good | FP8 | 7 GB | Moderate |
| AuraFlow 0.3 | Good | FP8 | 7 GB | Moderate |
| Stable Diffusion 3.5 Large (8B) | Usable | GGUF Q4 | 7 GB | Slow |
| Stable Diffusion 3.5 Large Turbo | Usable | GGUF Q4 | 7 GB | Slow |
| FLUX.1 Krea Dev | Usable | GGUF Q4 | 7 GB | Slow |
| Stable Diffusion 3.5 Medium (2.5B) | Usable | FP16 | 8 GB | Moderate |
| HunyuanDiT 1.5B | Usable | FP16 | 8 GB | Moderate |
| Flux.2 Klein 4B | Usable | FP8 | 8 GB | Moderate |
| Z-Image Base | Usable | FP8 | 8 GB | Moderate |
| HiDream-O1-Image 8.8B | Usable | FP8 | 8 GB | Moderate |
| Kolors | Usable | FP8 | 8 GB | Moderate |
| Krea 2 Turbo | Usable | GGUF Q4 | 8 GB | Slow |
| Flux.1 Dev 12B | Usable | GGUF Q4 | 8 GB | Slow |
| Flux.1 Schnell 12B | Usable | GGUF Q4 | 8 GB | Slow |
| HunyuanImage 3.0 | Usable | GGUF Q4 | 8 GB | Slow |
| Qwen-Image 2512 (20B) | Barely | Offload | 8 GB | Very Slow |
| Seedream 3.0 | Barely | Offload | 8 GB | Very Slow |
| GLM-Image | Barely | Offload | 8 GB | Very Slow |
| Flux.2 Dev 32B | Can't Run | — | needs 12 GB | — |
Image to Image
| Model | Rating | Runs as | VRAM used | Speed |
|---|---|---|---|---|
| SD 1.5 img2img | Good | FP16 | 4 GB | Fast |
| InstructPix2Pix | Good | FP16 | 5 GB | Moderate |
| Mage-Flow 4B | Good | GGUF Q4 | 4 GB | Moderate |
| SDXL img2img | Good | FP16 | 7 GB | Moderate |
| Boogu-Image Edit | Good | GGUF Q4 | 6 GB | Slow |
| LongCat-Image Edit | Good | GGUF Q4 | 6 GB | Slow |
| IP-Adapter FaceID SDXL | Usable | Offload | 6 GB | Very Slow |
| IP-Adapter SDXL | Usable | Offload | 6 GB | Very Slow |
| Flux.1 Dev img2img 12B | Usable | GGUF Q4 | 8 GB | Slow |
| Flux Kontext Dev | Usable | GGUF Q4 | 8 GB | Slow |
| Qwen-Image-Edit 2511 | Barely | Offload | 8 GB | Very Slow |
Inpainting
| Model | Rating | Runs as | VRAM used | Speed |
|---|---|---|---|---|
| SD 1.5 Inpainting | Good | FP16 | 4 GB | Fast |
| SDXL Inpainting | Good | FP16 | 7 GB | Moderate |
| PowerPaint v2.1 | Good | FP16 | 7 GB | Moderate |
| BrushNet | Usable | FP16 | 8 GB | Moderate |
| Flux.1 Fill Dev | Usable | GGUF Q4 | 8 GB | Slow |
ControlNet
| Model | Rating | Runs as | VRAM used | Speed |
|---|---|---|---|---|
| ControlNet SD 1.5 | Good | FP16 | 5 GB | Moderate |
| T2I-Adapter SDXL | Usable | FP16 | 8 GB | Moderate |
| ControlNet SDXL | Usable | Offload | 6 GB | Very Slow |
| ControlNet Flux | Barely | Offload | 8 GB | Very Slow |
Video
| Model | Rating | Runs as | VRAM used | Speed |
|---|---|---|---|---|
| Kandinsky 6.0 Video Lite 3B | Good | FP8 | 5 GB | Moderate |
| WAN 2.1 T2V 1.3B | Good | FP16 | 6 GB | Moderate |
| AnimateDiff Lightning | Good | FP16 | 6 GB | Moderate |
| AnimateDiff v3 (SD 1.5) | Good | FP16 | 6 GB | Moderate |
| ZeroScope v2 576w | Good | FP16 | 6 GB | Moderate |
| AnimateDiff V2V | Good | FP16 | 6 GB | Moderate |
| AnimateDiff I2V | Good | FP16 | 6 GB | Moderate |
| LTX-Video 0.9 (2B) | Good | FP8 | 6 GB | Moderate |
| LTX-Video I2V | Good | FP8 | 6 GB | Moderate |
| WAN 2.2 TI2V 5B | Good | FP8 | 7 GB | Moderate |
| Waver 1.0 | Good | FP8 | 7 GB | Moderate |
| Ovi 1.1 | Usable | Offload | 5 GB | Very Slow |
| SkyReels V3 R2V 14B | Usable | GGUF Q3 | 7 GB | Slow |
| Stable Video Diffusion 1.1 | Usable | FP16 | 8 GB | Moderate |
| CogVideoX 2B | Usable | FP16 | 8 GB | Moderate |
| ModelScope T2V | Usable | FP16 | 8 GB | Moderate |
| TokenFlow | Usable | FP16 | 8 GB | Moderate |
| Latte | Usable | FP16 | 8 GB | Moderate |
| SEINE | Usable | FP16 | 8 GB | Moderate |
| LongCat-Video 13.6B | Usable | Offload | 6 GB | Very Slow |
| CogVideoX 5B | Usable | FP8 | 8 GB | Moderate |
| CogVideoX 5B I2V | Usable | FP8 | 8 GB | Moderate |
| SkyReels V1 | Usable | FP8 | 8 GB | Moderate |
| SkyReels V1 I2V | Usable | FP8 | 8 GB | Moderate |
| Wan-Dancer 14B | Usable | Offload | 7 GB | Very Slow |
| HuMo 17B | Usable | Offload | 7 GB | Very Slow |
| WAN 2.2 T2V A14B (MoE) | Usable | GGUF Q4 | 8 GB | Slow |
| WAN 2.2 I2V A14B | Usable | GGUF Q4 | 8 GB | Slow |
| WAN 2.1 T2V 14B | Usable | GGUF Q4 | 8 GB | Slow |
| WAN 2.1 I2V 480P 14B | Usable | GGUF Q4 | 8 GB | Slow |
| WAN 2.1 V2V | Usable | GGUF Q4 | 8 GB | Slow |
| HunyuanVideo T2V v1.5 | Usable | GGUF Q4 | 8 GB | Slow |
| HunyuanVideo I2V v1.5 | Usable | GGUF Q4 | 8 GB | Slow |
| HunyuanVideo 13B T2V | Usable | GGUF Q4 | 8 GB | Slow |
| HunyuanVideo I2V | Usable | GGUF Q4 | 8 GB | Slow |
| Wan 2.2 S2V 14B | Usable | GGUF Q3 | 8 GB | Slow |
| WAN 2.1 I2V 720P 14B | Usable | GGUF Q3 | 8 GB | Slow |
| Wan-Animate-2 14B | Usable | GGUF Q3 | 8 GB | Slow |
| SCAIL-2 14B | Usable | GGUF Q3 | 8 GB | Slow |
| MiniMax H3 FL2VA | Barely | Offload | 8 GB | Very Slow |
| MiniMax H3 Ref2VA | Barely | Offload | 8 GB | Very Slow |
| Wan 2.2 Animate 14B | Barely | Offload | 8 GB | Very Slow |
| LTX-2.5 22B | Barely | Offload | 8 GB | Very Slow |
| LTX-2.3 22B | Barely | Offload | 8 GB | Very Slow |
| LTX-2 19B | Barely | Offload | 8 GB | Very Slow |
| FramePack I2V HY FP8 | Barely | Offload | 8 GB | Very Slow |
| Stable Video Diffusion XT 1.1 (25 frames) | Barely | Offload | 8 GB | Very Slow |
| DynamiCrafter 512 | Barely | Offload | 8 GB | Very Slow |
| AnimateDiff SDXL | Barely | Offload | 8 GB | Very Slow |
| LTX-Video 13B | Can't Run | — | needs 12 GB | — |
| MOVA | Can't Run | — | needs 29 GB | — |
| Mochi 1 10B | Can't Run | — | needs 16 GB | — |
| Open-Sora 2.0 (11B) | Can't Run | — | needs 12 GB | — |
| MAGI-1 | Can't Run | — | needs 12 GB | — |
| DynamiCrafter 1024 | Can't Run | — | needs 12 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 | Good | FP16 | 4 GB | Fast |
| SeedVR2 3B | Good | FP8 | 5 GB | Moderate |
| SeedVR2 7B | Usable | FP8 | 8 GB | Moderate |
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 | Good | FP16 | 4 GB | Fast |
| Shap-E | Good | FP16 | 4 GB | Fast |
| InstantMesh | Good | FP16 | 6 GB | Moderate |
| Zero123++ v1.2 | Good | FP16 | 6 GB | Moderate |
| LGM | Usable | FP16 | 8 GB | Moderate |
| One-2-3-45 | Usable | FP16 | 8 GB | Moderate |
| SV3D | Usable | Offload | 6 GB | Very Slow |
| Hunyuan3D 2.0 | Usable | FP8 | 8 GB | Moderate |
| TRELLIS.2 4B | Can't Run | — | needs 12 GB | — |
| Pixal3D | Can't Run | — | needs 10 GB | — |
| Hunyuan3D 2.1 | Can't Run | — | needs 10 GB | — |
| 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 | Good | FP16 | 3 GB | Fast |
| Stable Audio 3 Small-SFX | Good | FP16 | 3 GB | Fast |
| Whisper Large v3 | Good | FP16 | 4 GB | Fast |
| Chatterbox Multilingual | Good | FP16 | 4 GB | Fast |
| MMAudio Large 44k | Good | FP16 | 4 GB | Fast |
| Stable Audio Open | Good | FP16 | 4 GB | Fast |
| Qwen3-TTS 1.7B | Good | FP16 | 5 GB | Moderate |
| MusicGen Medium (1.5B) | Good | FP16 | 6 GB | Moderate |
| IndexTTS 2.5 | Good | FP16 | 6 GB | Moderate |
| VibeVoice 1.5B | Good | FP16 | 7 GB | Moderate |
| Stable Audio 3 Medium | Good | FP16 | 7 GB | Moderate |
| Fish Audio S2 Pro 4B | Usable | GGUF Q4 | 7 GB | Slow |
| ACE-Step 1.5 Turbo | Usable | FP16 | 8 GB | Moderate |
| Bark | Usable | FP16 | 8 GB | Moderate |
| MusicGen Large (3.3B) | Usable | Offload | 6 GB | Very Slow |
| YuE2 3B | Barely | Offload | 8 GB | Very Slow |
| MiniMax Music 3 | Barely | Offload | 8 GB | Very Slow |
Frequently asked questions
How much VRAM does the NVIDIA RTX 4060 Ti 8GB have?
The NVIDIA RTX 4060 Ti 8GB has 8 GB of VRAM with 288 GB/s of memory bandwidth.
What AI models can the NVIDIA RTX 4060 Ti 8GB run?
It can run 157 of the 168 AI models we track: 13 perfectly (S), 1 great (A), 68 good (B), 58 usable (C) and 17 barely (D). 11 need more VRAM than it has.
Can the NVIDIA RTX 4060 Ti 8GB run MiniMax H3 FL2VA?
Yes, with CPU offloading (rating D, barely).
Can the NVIDIA RTX 4060 Ti 8GB run MiniMax H3 Ref2VA?
Yes, with CPU offloading (rating D, barely).
Can the NVIDIA RTX 4060 Ti 8GB run Qwen-Image 2.1?
Yes, in FP8 (rating B, good).
Can the NVIDIA RTX 4060 Ti 8GB run Z-Image Turbo?
Yes, in FP8 (rating B, good).