§01·spec · /gpus
RTX 4060
nvidia40 series8GB VRAM
§02·models that run on this GPU
5 total| Model | Vertical | Best speed | Min VRAM | Works | Benchmarks | |
|---|---|---|---|---|---|---|
| AnimateDiff | video | 6GB | ✓ | 1 | check ↗ | |
| CogVideoX 1.5 | video | 8GB | ✓ | 1 | check ↗ | |
| HunyuanVideo | video | 8GB | ✓ | 1 | check ↗ | |
| LTX Video 2.3 | video | 8GB | ✓ | 1 | check ↗ | |
| Wan Video 2.1 1.3B | video | 6GB | ✓ | 1 | check ↗ |
§03·tested recipes
showing 6 of 9- ttsintermediate8GB+recipe
Foundation-1 on RTX 4060: Structured Music Sample Generation at the 8 GB Floor
- ttsbeginner5GB+recipe
VoxCPM on RTX 4060: Zero-Shot Voice Cloning TTS in ~5 GB VRAM
- ttsintermediate4GB+recipe
OmniVoice on RTX 4060: Zero-Shot Voice Cloning Across 646 Languages in 8 GB
- ttsintermediate5GB+recipe
OpenAudio S1 Mini on RTX 4060: 13-Language Distilled TTS in ~5 GB VRAM
- llmbeginner4GB+recipe
Qwen3-4B on RTX 4060: Q4_K_M GGUF via Ollama or llama.cpp
- multimodalbeginner6GB+recipe
Gemma 4 E4B on RTX 4060: Multimodal Inference via Q4_K_M GGUF (llama.cpp or Ollama)