Harshit Goyal

harshit-genrius

AI & ML interests

None yet

Recent Activity

liked a Space about 4 hours ago

Genrius-AI/llm-vram-calculator

updated a collection about 5 hours ago

Pingala-8: 2-bit LLMs for llama.cpp

updated a Space about 5 hours ago

Genrius-AI/llm-vram-calculator

View all activity

Organizations

liked a Space about 4 hours ago

LLM GPU fit: Pingala-8 2-bit vs 4-bit

🧮

Will a model fit your GPU as Pingala-8 2-bit or Q4_K_M?

updated a collection about 5 hours ago

Pingala-8: 2-bit LLMs for llama.cpp

Collection

Our 2-bit GGUF format: Qwen3-4B and Llama-3.1-8B, 85% smaller, no retraining. Needs our patched llama.cpp (CUDA). • 5 items • Updated about 5 hours ago

updated a Space about 5 hours ago

LLM GPU fit: Pingala-8 2-bit vs 4-bit

🧮

Will a model fit your GPU as Pingala-8 2-bit or Q4_K_M?

published a Space about 5 hours ago

LLM GPU fit: Pingala-8 2-bit vs 4-bit

🧮

Will a model fit your GPU as Pingala-8 2-bit or Q4_K_M?

updated a collection about 10 hours ago

Pingala-8: 2-bit LLMs for llama.cpp

Collection

Our 2-bit GGUF format: Qwen3-4B and Llama-3.1-8B, 85% smaller, no retraining. Needs our patched llama.cpp (CUDA). • 5 items • Updated about 5 hours ago

updated a Space about 10 hours ago

README

🚀

published a Space about 10 hours ago

README

🚀

updated a dataset about 10 hours ago

Genrius-AI/pingala8-benchmarks

Viewer • Updated about 7 hours ago • 30

published a dataset about 10 hours ago

Genrius-AI/pingala8-benchmarks

Viewer • Updated about 7 hours ago • 30

updated a collection about 10 hours ago

Pingala-8: 2-bit LLMs for llama.cpp

Collection

Our 2-bit GGUF format: Qwen3-4B and Llama-3.1-8B, 85% smaller, no retraining. Needs our patched llama.cpp (CUDA). • 5 items • Updated about 5 hours ago

updated 2 models about 10 hours ago

Genrius-AI/Llama-3.1-8B-Pingala8-2bit

Text Generation • 3B • Updated about 4 hours ago • 124 • 1

Genrius-AI/Qwen3-4B-Pingala8-2bit

Text Generation • 1B • Updated about 4 hours ago • 89

updated a Space about 10 hours ago

Pingala-8 2-bit LLMs

📉

2-bit GGUF LLMs for llama.cpp, 85% smaller, no retraining

published a Space about 10 hours ago

Pingala-8 2-bit LLMs

📉

2-bit GGUF LLMs for llama.cpp, 85% smaller, no retraining

published 2 models 6 days ago

Genrius-AI/Llama-3.1-8B-Pingala8-2bit

Text Generation • 3B • Updated about 4 hours ago • 124 • 1

Genrius-AI/Qwen3-4B-Pingala8-2bit

Text Generation • 1B • Updated about 4 hours ago • 89

updated 2 models 6 days ago

Genrius-AI/Llama-3.1-8B-Pingala8-2bit

Text Generation • 3B • Updated about 4 hours ago • 124 • 1

Genrius-AI/Qwen3-4B-Pingala8-2bit

Text Generation • 1B • Updated about 4 hours ago • 89

Harshit Goyal

AI & ML interests

Recent Activity

Organizations

harshit-genrius's activity

LLM GPU fit: Pingala-8 2-bit vs 4-bit

LLM GPU fit: Pingala-8 2-bit vs 4-bit

LLM GPU fit: Pingala-8 2-bit vs 4-bit

README

README

Pingala-8 2-bit LLMs

Pingala-8 2-bit LLMs