Julian Neytchev
dobriak
AI & ML interests
cybersecurity modeling
Recent Activity
upvoted a collection 1 day ago
Gemma 4 QAT Q4_0 reacted to danielhanchen's post with 👍 2 days ago
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: https://huggingface.co/unsloth/gemma-4-12b-it-GGUF
Guide: https://unsloth.ai/docs/models/gemma-4 reacted to danielhanchen's post with 🔥 2 days ago
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: https://huggingface.co/unsloth/gemma-4-12b-it-GGUF
Guide: https://unsloth.ai/docs/models/gemma-4Organizations
None yet
Noticeable Performance Decrease
👍 3
4
#23 opened 20 days ago
by 
WebWeaverWraith
Success with RTX-5090, cuda 13.2, vllm 0.20.2
🚀👍 6
2
#1 opened about 1 month ago
by dobriak