Alberto Cetoli's picture

Alberto Cetoli PRO

fractalego

·

https://fractalego.social/@alberto

AI & ML interests

Entity/relation extraction, Q&A, Summarisation

Recent Activity

upvoted a paper 5 days ago

GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models

liked a model 12 days ago

openai/gpt-oss-20b

reacted to mitkox's post with 😎 24 days ago

I run Qwen3-Coder 480B locally on my Z8, with a 1-million token context window. It’s the equivalent of parallel-parking a Nimitz-class carrier in a kiddie pool. Thanks to whatever dark pact the llama.cpp, CUDA, and kernel folks signed, hybrid inferencing + VRAM↔RAM offload let me stream the model’s synapses across Xeon, RAM, and four lonely A6000s without summoning either the OOM killer or a small house fire.

View all activity

Organizations

New activity in togethercomputer/GPT-JT-6B-v1 over 2 years ago

8bit quantization

#12 opened over 2 years ago by deleted