Oliver Prompts @oliviscusAI

2 of this account's posts made the board, 1 reached the top 3.

Stories from this source

AirLLM runs big models on low VRAM

AirLLM uses layer-wise inference to run 70B models on 4GB GPUs and 405B on 8GB, supporting Llama, Qwen and Mistral, now open source.

Open Source Peaked at #2 @oliviscusAI Oct 11, 12:22
Open-source local image-to-3D app Modly

Modly is a free open-source desktop app that turns photos into 3D meshes locally on your GPU, no cloud or subscription.

Open Source Peaked at #8 @oliviscusAI Oct 10, 09:27