8000 Llama.cpp 30B runs with only 6GB of RAM now - update ? · Issue #182 · antimatter15/alpaca.cpp · GitHub
[go: up one dir, main page]

Skip to content
Llama.cpp 30B runs with only 6GB of RAM now - update ? #182
@magicmars35

Description

@magicmars35

Llama.cpp 30B runs with only 6GB of RAM now :

ggml-org#613

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions

      0