gpt4all
Docker app from grtgbln's Repository
Overview
An all-in-one LLM server and chat UI
Requirements
Requires an Nvidia GPU.
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).
Runtime arguments
- Network
bridge- Privileged
- true
- Extra Params
--gpus all --shm-size 1g
Template configuration
HuggingFace TokenVariable
The HuggingFace token to use
- Target
- HUGGING_FACE_HUB_TOKEN
API PortPorttcp
Container Port: 8080
- Target
- 80
- Default
- 8080
- Value
- 8080
Data PathPathrw
Data directory
- Target
- /data
- Default
- /mnt/user/appdata/gpt4all/data
- Value
- /mnt/user/appdata/gpt4all/data
Use flash attentionVariable
Use flash attention
- Target
- USE_FLASH_ATTENTION
- Default
- false|true
Categories
Details
Repository
ghcr.io/huggingface/text-generation-inference:latestRegistry
Last Updated2026-05-31
First Seen2024-07-11
Run Gpt4all on Unraid.
Gpt4all is listed in Community Apps for Unraid OS. Explore Unraid to build a flexible home server, NAS, or homelab.