6gb-vram

Here are 2 public repositories matching this topic...

Offline GPU-accelerated audio ML pipeline. faster-whisper + cross-encoder reranking + FFmpeg. Runs on 6GB VRAM.

open-source ffmpeg audio-editing podcasts transcripts fastapi creator-tools whisper-asr 6gb-vram

A fully local OpenCode + llama.cpp + Ornith 1.5 coding-agent setup tuned for 128K context on a tight 6 GB VRAM budget.

windows opencode cuda long-context llama-cpp local-llm coding-agent 6gb-vram ornith

To associate your repository with the 6gb-vram topic, visit your repo's landing page and select "manage topics."