Hugging Face's logo
Activity Feed

AI & ML interests

None defined yet.

Recent Activity
harshit-genrius  updated a collection 6 days ago
Pingala-8: 2-bit LLMs for llama.cpp
harshit-genrius  updated a dataset 7 days ago
Genrius-AI/pingala8-benchmarks
harshit-genrius  updated a collection 7 days ago
2-bit GGUFs that fit a 12 GB GPU (measured)
View all activity

Genrius-AI 's collections 2

Pingala-8: 2-bit LLMs for llama.cpp
2-bit GGUFs for llama.cpp: Qwen3.8-27B in 8.31 GB (fits a 12 GB GPU), Qwen3.5 4B/2B/0.8B, Qwen3 4B/1.7B/0.6B, Llama-3.1-8B, GPU fit calculator.
Pingala-8: 2-bit LLMs for llama.cpp
2-bit GGUFs for llama.cpp: Qwen3.8-27B in 8.31 GB (fits a 12 GB GPU), Qwen3.5 4B/2B/0.8B, Qwen3 4B/1.7B/0.6B, Llama-3.1-8B, GPU fit calculator.