A workflow reportedly gets flagship local LLMs running on an 8GB GPU
XDA Developers says a workflow lets its writer run flagship local LLMs on an 8GB GPU they say shouldn't be able to handle them.
TLDR
XDA Developers says its writer can run flagship local large language models on an 8GB GPU using a workflow, despite saying the GPU shouldn't be able to run them. The writer says they aren't shopping for a new GPU just yet.
Combined views
6.7K
1 Source, first seen 8h ago
17 likes
