§01·spec · /gpus
RTX 5060
nvidia50 series8GB VRAM
11 open-weights AI models run on the RTX 5060 — see which fit, how fast they go, and the VRAM each needs.
§02·models that run on this GPU
11 totalMultimodal · 2
| Model | Best speed | Min VRAM | Works | Evidence | |
|---|---|---|---|---|---|
| Gemma 4 E4B-IT | 6GB | ✓ | recipe | check ↗ | |
| MiniMind-O | 4GB | ✓ | recipe | check ↗ |
TTS · 5
| Model | Best speed | Min VRAM | Works | Evidence | |
|---|---|---|---|---|---|
| Foundation-1 | 8GB | ✓ | recipe | check ↗ | |
| Kokoro TTS | 2GB | ✓ | recipe | check ↗ | |
| OmniVoice | 4GB | ✓ | recipe | check ↗ | |
| OpenAudio S1 Mini | 5GB | ✓ | recipe | check ↗ | |
| VoxCPM | 5GB | ✓ | recipe | check ↗ |
§03·tested recipes
showing 6 of 11- llmintermediate8GB+recipe
Ornith 1.0 9B on RTX 5060 (8GB): Local Agentic Coding at the Fit Boundary via llama.cpp + OpenHands
- imageintermediate8GB+recipe
Anima 2B on RTX 5060: 8GB Anime Text-to-Image via INT8 ConvRot in ComfyUI
- multimodalbeginner6GB+recipe
Gemma 4 E4B on RTX 5060: Multimodal Inference via Q4_K_M GGUF (llama.cpp or Ollama)
- specializedbeginner4GB+recipe
SAM 3 on RTX 5060: Promptable Image and Video Segmentation
- multimodalintermediate4GB+recipe
MiniMind-O on RTX 5060: 0.1B Omni Model (Text + Speech + Image In/Out)
- ttsintermediate8GB+recipe
Foundation-1 on RTX 5060: Structured Music Sample Generation at the 8 GB Floor