3 30 931

john smith

k249

AI & ML interests

None yet

Recent Activity

updated a collection about 24 hours ago

med

liked a model about 24 hours ago

EPFLiGHT/Meditron3-70B

liked a model about 24 hours ago

noctrex/The-Philosopher-Zephyr-7B-GGUF

View all activity

Organizations

None yet

updated a collection about 24 hours ago

med

Collection

354 items • Updated about 24 hours ago • 1

liked 2 models about 24 hours ago

EPFLiGHT/Meditron3-70B

Text Generation • 71B • Updated 29 days ago • 5.32k • 25

noctrex/The-Philosopher-Zephyr-7B-GGUF

7B • Updated Nov 17, 2025 • 11 • 2

liked a model 1 day ago

noctrex/gemma-4-26B-A4B-it-MXFP4_MOE-GGUF

Image-Text-to-Text • 25B • Updated May 4 • 8.82k • 18

liked a model 2 days ago

SupraLabs/Supra-50M-Reasoning

Text Generation • 51.8M • Updated 3 days ago • 808 • 30

liked a Space 2 days ago

Open SLM Leaderboard

🏆

Open Small Language Model Leaderboard

liked 3 models 2 days ago

reacted to danielhanchen's post with 👍 2 days ago

Post

8421

Gemma 4 12B can now run locally on just 8GB RAM via Dynamic GGUFs.

Google's new model, Gemma 4 12B Unified supports image, audio and 256K context.
You can run and train the model via Unsloth Studio.

GGUF: unsloth/gemma-4-12b-it-GGUF
Guide: https://unsloth.ai/docs/models/gemma-4