arc-llama
View repository ↗

A quick look · Arc Llama 0.9.1.2

From your Arc GPU
to your next conversation.

Find a model. Check the runtime. Open chat.

Start with a clear next step. One home for finding models, reviewing your setup, and opening chat.
01 / 06

Start with a clear next step.

One home for finding models, reviewing your setup, and opening chat.

Find your next model. Search Hugging Face with recognizable publishers and plain-language download choices.
02 / 06

Find your next model.

Search Hugging Face with recognizable publishers and plain-language download choices.

Check the runtime before the download. Memory fit and architecture support answer different questions.
03 / 06

Check the runtime before the download.

Memory fit and architecture support answer different questions.

Review before you run. See the selected model, GPU, context, and estimated memory use together.
04 / 06

Review before you run.

See the selected model, GPU, context, and estimated memory use together.

Make it a conversation. Chat with your selected model in a focused interface.
05 / 06

Make it a conversation.

Chat with your selected model in a focused interface.

Keep your setup in view. Check GPU status and measurements from actual requests.
06 / 06

Keep your setup in view.

Check GPU status and measurements from actual requests.