Radamés Ajna's picture

Radamés Ajna

radames

AI & ML interests

None yet

Recent Activity

View all activity

Organizations

Spaces-explorers's profile picture CVPR Demo Track's profile picture MONAI's profile picture Gradio-Blocks-Party's profile picture Webhooks Explorers (BETA)'s profile picture Open Access AI Collective's profile picture The Team Ten's profile picture Open-Source AI Meetup's profile picture Stable Diffusion concepts library's profile picture Stable Diffusion Dreambooth Concepts Library's profile picture Daily's profile picture DragGan's profile picture meta-private's profile picture temp-org's profile picture Blog-explorers's profile picture Editing Images's profile picture leditsplusplus's profile picture sci-blender's profile picture Lilac AI's profile picture Latent Consistency's profile picture rtemp's profile picture ZeroGPU Explorers's profile picture cvmistralhackathon's profile picture Shizuku's profile picture Journalists on Hugging Face's profile picture Hugging Face - Visual Blocks's profile picture Social Post Explorers's profile picture +RAIN film festival's profile picture Agents-MCP-Hackathon's profile picture

radames's activity

reacted to cbensimon's post with 👍👀🤗🚀🔥 2 days ago
view post
Post
5654
🚀 ZeroGPU medium size is now available as a power-user feature

Nothing too fancy for now—ZeroGPU Spaces still default to large (70GB VRAM)—but this paves the way for:
- 💰 size-based quotas / pricing (medium will offer significantly more usage than large)
- 🦣 the upcoming xlarge size (141GB VRAM)

You can as of now control GPU size via a Space variable. Accepted values:
- auto (future default)
- medium
- large (current default)

The auto mode checks total CUDA tensor size during startup:
- More than 30GB → large
- Otherwise → medium
·
upvoted an article 3 days ago
view article
Article

Tiny Agents in Python: a MCP-powered agent in ~70 lines of code

By celinah and 3 others
95
New activity in Xenova/jinja-playground 22 days ago