CLI reference

<!-- Generated from clap definitions by mistralrs-cli docgen. Do not edit. -->

Subcommands

Subcommand	Purpose
mistralrs serve	Start HTTP/MCP server and (optionally) the UI at /ui
mistralrs run	Run model in interactive mode, or one-shot mode with -i
mistralrs completions	Generate shell completions
mistralrs quantize	Generate UQFF quantized model file
mistralrs doctor	Run system diagnostics and environment checks
mistralrs tune	Recommend quantization + device mapping for a model. Rejects --quant auto; pass --quant <level> or --isq <level> to bias the recommendation toward a specific quantization target
mistralrs login	Authenticate with HuggingFace Hub
mistralrs cache	Manage the HuggingFace model cache
mistralrs bench	Run performance benchmarks for plain model generation
mistralrs from-config	Run from a full TOML configuration file
mistralrs update	Update a prebuilt install to the latest release
mistralrs uninstall	Remove a prebuilt install

Global options

Option	Default	Description
--seed <SEED>		Random seed for reproducibility
-l, --log <LOG>		Log all requests and responses to this file
--token-source <TOKEN_SOURCE>	cache	Token source for HuggingFace authentication. Formats: literal:<token>, env:<var>, path:<file>, cache, none
-v, --verbose	0	Increase logging verbosity. Use -v for debug and -vv for trace-level internals