gpt4all ghcr.io/huggingface/text-generation-inference:latest https://github.com/huggingface/text-generation-inference/pkgs/container/text-generation-inference bridge true https://github.com/nomic-ai/gpt4all/issues https://www.nomic.ai/gpt4all An all-in-one LLM server and chat UI False AI: Productivity: Tools: Other: Status:Stable https://raw.githubusercontent.com/nwithan8/unraid_templates/master/images/gpt4all-icon.png https://raw.githubusercontent.com/nwithan8/unraid_templates/main/templates/gpt4all.xml https://github.com/nwithan8 Requires an Nvidia GPU. [br] In **Post Arguments**, replace `$MODEL` with the model you want to host and `$NUM_SHARD` with the number of shards you want to use (recommended: 1). ### 2024-07-10 Initial release --gpus all --shm-size 1g --model-id $MODEL --num-shard $NUM_SHARD 8080 /mnt/user/appdata/gpt4all/data