I wish to share a nice resource I just found:
-- LLMs for local use list (and tentative ranking); VRAM calculator according to quantization and context size; technical details such as Architecture, Knowledge Cutoff, Number of Layers, Attention Structure etc.
I wish to share a nice resource I just found:
-- LLMs for local use list (and tentative ranking); VRAM calculator according to quantization and context size; technical details such as Architecture, Knowledge Cutoff, Number of Layers, Attention Structure etc.