docs: simplify spec-type configuration in gemma-4-12B preset

docs: remove Gemma-4-12B-Agentic and Qwopus3.8-27B-Flash-V2 from model groups

docs: remove FOUNDATION and MAGI rules documentation files

docs: uncomment np setting in multiple model configuration files

docs: uncomment np setting in gemma-4-12B configuration

docs: comment out Qwopus3.8-27B-Flash-V2 model configuration in llama-swap.yaml

docs: comment out Gemma-4-12B-Agentic model configuration in llama-swap.yaml

docs: update model-draft path for Gemma-4-12B-Agentic configuration

docs: update model-draft path and remove ngram-mod specifications in Gemma-4-12B-Agentic configuration

docs: correct draft-model key to model-draft in gemma-4-12B-Agentic configuration

docs: add draft-model path for Gemma-4-12B-Agentic in configuration

docs: revert context size to 131072 in qwen3.6-35b-mtp.ini

docs: add configurations for Gemma-4-12B-Agentic and Qwopus3.8-27B-Flash-V2 models in respective ini files

docs: update context size to 262144 in qwen3.6-35b-mtp.ini and llama-swap.yaml

docs: uncomment ctx-checkpoints and checkpoint-min-step in gemma-4-26b-a4b-it-qat-mtp.ini

docs: update ngram-mod specifications in gemma-4-26b-a4b-it-qat-mtp.ini

docs: update context size for Qwen3.6-35B model in llama-swap.yaml

docs: remove Qwen3.8-27B-Pi model configuration and add FOUNDATION rules for local models

docs: comment out 'np' parameter in multiple configuration files

docs: add ngram-mod specifications to qwen3.6-35b-mtp.ini

docs: add ngram-mod specifications to gemma-4-26b-a4b-it-qat-mtp.ini

docs: add ngram-mod specifications to gemma-4-12b-it-qat.ini

docs: increase context size to 131072 in qwen3.6-35b-mtp.ini

docs: adjust context size and spec parameters in qwen3.6-35b-mtp.ini

docs: update globalConcurrencyLimit and concurrencyLimit to 0 in llama-swap.yaml

docs: update concurrency limits to 0 in multiple configuration files and add new parameters in gemma and qwen presets

docs: update concurrency limits and context sizes in multiple configuration files

docs: update globalConcurrencyLimit to 1 in llama-swap.yaml

docs: update globalConcurrencyLimit to 0 in llama-swap.yaml

docs: update concurrencyLimit to 0 in llama-swap.yaml and manage-models.py

docs: update device-draft and mmproj-device settings in multiple model configuration files

docs: update context sizes and device settings in multiple model configuration files

docs: update device-draft and mmproj-device settings in qwen3.6-35b-mtp.ini

docs: correct mmproj-device setting in gemma-4-12b-it-qat.ini

docs: update device settings for draft and mmproj in gemma-4-12b-it-qat.ini

docs: update context sizes and device settings in multiple model configuration files

docs: update context size for Qwen3.6-35B model in llama-swap.yaml

docs: update spec-draft-n-max to 4 in gemma-4-12b-it-qat.ini

docs: simplify spec-type in gemma-4-12b-it-qat.ini and remove unused parameters

docs: update spec-draft-n-max to 2 and comment out unused checkpoint settings in gemma-4-12b-it-qat.ini

docs: update spec-draft-n-max to 2 in qwen3.6-35b-mtp.ini

docs: update concurrencyLimit to 1 for model entries in llama-swap.yaml and manage-models.py

docs: enable metrics in various INI files and add MAGI rules for local models

docs: enhance manage-models.py to support Stable Diffusion model configuration and update README.md with usage examples

docs: remove unused Laya configuration and clean up commented-out model definitions in llama-swap.yaml

docs: enhance argument parser in manage-models.py with detailed usage examples and overrides

docs: enhance argument parser in manage-models.py with examples and help formatting

docs: update README.md with manage-models.py usage and enhance rpc-server.sh error handling

docs: remove Gemma-4-12B-Agentic configuration from llama-swap.yaml for cleanup

docs: update hf reference in gemma-4-12b-agentic-fable5.ini for version consistency