Skip to content

ujust ollama

Local LLM inference server with GPU acceleration

Quick Start

Follow the standard service lifecycle:

Step Command Recording
1. Config ujust ollama config
2. Start ujust ollama start
3. Status ujust ollama status
4. Logs ujust ollama logs
5. Stop ujust ollama stop

Subcommands

Configuration

Subcommand Arguments Description Recording
config Configure server

Lifecycle

Subcommand Arguments Description Recording
restart Restart server
start Start Ollama server
stop Stop Ollama server
delete Remove server config and container

Monitoring

Subcommand Arguments Description Recording
status Show server/container status
logs [--lines=N] View container logs

Operations

Subcommand Arguments Description Recording
list List installed models
pull --model=NAME Download model from Ollama registry
run --model=NAME Run model

Shell

Subcommand Arguments Description Recording
shell [-- CMD] Open shell or execute command in container

Other

Subcommand Arguments Description Recording
help Show help

Flags

Flag Short Default Values Description
--bind -b
--config-dir -c
--context-length
--gpu-type -g
--image -i
--instance -n
--lines -l
--model -m
--port -p
--prompt
--tag -t
--workspace-dir -w

See Also

View all 11 command recordings for this service.


Source: just/bazzite-ai/ollama.just