self-hosted/ai
§01·spec · /gpus

RTX 4060

nvidia40 series8GB VRAM

12 open-weights AI models run on the RTX 4060 — see which fit, how fast they go, and the VRAM each needs.

§02·models that run on this GPU
12 total
LLM · 4
ModelBest speedMin VRAMWorksEvidence
Gemma 4 12B8GBrecipecheck ↗
Mistral Nemo 12B8GBrecipecheck ↗
Ornith 1.0 9B8GBrecipecheck ↗
Qwen3-4B4GBrecipecheck ↗
Multimodal · 2
ModelBest speedMin VRAMWorksEvidence
Gemma 4 E4B-IT6GBrecipecheck ↗
MiniMind-O4GBrecipecheck ↗
TTS · 5
specialized · 1
ModelBest speedMin VRAMWorksEvidence
SAM 34GBrecipecheck ↗
§03·tested recipes
showing 6 of 12