GPU Vault model library

Find a model. Launch it on the right GPU.

Browse currently supported Hugging Face and official ComfyUI models, compare the hardware profile, and review a live GPU offer before spending credits.

Sort

Launchable models

6 launchable models matching “RichardErkhov” on this page. Exact, runtime-qualified revisions only.

text generationRichardErkhov

gradientai_-_gradient-tinystories-20m-8bits

gradientai_-_gradient-tinystories-20m-8bits is a validated text generation model.

1× GPU · 16 GB VRAM19.8M params 98

text generationRichardErkhov

gradientai_-_gradient-tinystories-20m-4bits

gradientai_-_gradient-tinystories-20m-4bits is a validated text generation model.

1× GPU · 16 GB VRAM19.9M params 95

text generationRichardErkhov

HuggingFaceH4_-_mistral-7b-anthropic-4bits

HuggingFaceH4_-_mistral-7b-anthropic-4bits is a validated text generation model.

1× GPU · 24 GB VRAM7.4B params 93

text generationRichardErkhov

HuggingFaceH4_-_mistral-7b-anthropic-8bits

HuggingFaceH4_-_mistral-7b-anthropic-8bits is a validated text generation model.

1× GPU · 24 GB VRAM7.2B params 92

text generationRichardErkhov

stabilityai_-_japanese-stablelm-instruct-gamma-7b-4bits

stabilityai_-_japanese-stablelm-instruct-gamma-7b-4bits is a validated text generation model.

1× GPU · 24 GB VRAM7.4B params 48

text generationRichardErkhov

stabilityai_-_japanese-stablelm-instruct-gamma-7b-8bits

stabilityai_-_japanese-stablelm-instruct-gamma-7b-8bits is a validated text generation model.

1× GPU · 24 GB VRAM7.2B params 48