PRIMA.CPP: Speeding Up 70B-Scale LLM Inference on Low-Resource Everyday Home Clusters
Paper
•
2504.08791
•
Published
•
117
cgus
cgus
AI & ML interests
Small general-purpose LLMs for text-translation/summarization/limited scenario generation.
Image-generation, mainly lightweight models such as SD1.5.
Occasionally making exl2/GGUF quants on my personal hardware (up to 14B).
Recent Activity
liked
a model
about 23 hours ago
OnomaAIResearch/Illustrious-Lumina-v0.03
updated
a model
2 days ago
cgus/granite-3.3-2b-instruct-exl2
published
a model
2 days ago
cgus/granite-3.3-2b-instruct-exl2
Organizations
None yet