How noelthirtyfour/llama-model-manager works
llama-model-manager is a Linux command-line toolkit for managing llama.cpp models and adapting runtime settings to available hardware. The principal workflow is to maintain model presets, select a backend and memory policy, then run llama-server through the llama-main service. It also covers model acquisition and tuning, llama.cpp updates, and OpenCode configuration export. The available evidence is the README and file tree only; relationships below are limited to documented behavior, and the implementation details inside the two scripts could not be inspected.
Main entry points: llama-modelctl Model CLI · llama-hw-select Hardware selector · 10-auto-hardware.conf Service hook
Components 18
Model management
- Model CLI
bin/llama-modelctl - Model catalog
- Model files
- Model acquisition
bin/llama-modelctl - Model parameters
bin/llama-modelctl - Adaptive tuning
bin/llama-modelctl
Hardware and runtime
- Hardware selector
bin/llama-hw-select - Service hook
systemd/10-auto-hardware.conf - Backend and profiles
bin/llama-modelctl - Runtime state
- llama-main
- llama-server
Operations and integrations
- llama.cpp updater
bin/llama-modelctl - OpenCode exporter
bin/llama-modelctl
Other components
- Operator
- Host hardware
- Hugging Face
- Remote OpenCode
Connections 21
- Operator → Model CLI: runs commands
README.md - Model CLI → Model catalog: manages presets
README.md - Model CLI → Model acquisition: adds models
README.md - Model acquisition → Hugging Face: downloads from
README.md - Model acquisition → Model files: stores models
README.md - Model CLI → Model parameters: sets parameters
README.md - Model parameters → Model catalog: updates presets
README.md - Model CLI → Adaptive tuning: runs tuning
README.md - Adaptive tuning → llama-server: benchmarks with
README.md - Operator → Hardware selector: runs selection
README.md - Service hook → Hardware selector: invokes at start
README.md - Hardware selector → Host hardware: detects devices
README.md - Hardware selector → Model catalog: rewrites runtime settings
README.md - Model CLI → Backend and profiles: sets policy
README.md - Backend and profiles → Runtime state: persists preferences
README.md - Hardware selector → Runtime state: uses policy
README.md - llama-main → llama-server: runs
README.md - Operator → llama.cpp updater: requests update
README.md - llama.cpp updater → llama-main: restarts
README.md - Operator → OpenCode exporter: requests export
README.md - OpenCode exporter → Remote OpenCode: generates configuration for
README.md