chore(model gallery): 🤖 add 1 new models via gallery agent

gallery/index.yaml

@@ -1,4 +1,29 @@
 ---
+- name: "ltx2"
+  url: "github:mudler/LocalAI/gallery/virtual.yaml@master"
+  urls:
+    - https://huggingface.co/convertor/ltx2-gguf
+  description: |
+    The model `convertor/ltx2-gguf` is a quantized version of the original Lightricks/LTX-2 model. It is designed for efficient deployment and inference, optimized for performance and reduced memory usage. While it is labeled as "dev (test)" and "distilled (test)" in the readme, it is based on the original LTX-2 model, which is known for its capabilities in tasks like text generation and classification. The quantized version retains the core functionality of the base model but may have been adapted for specific use cases or optimizations. For detailed technical specifications, refer to the original LTX-2 repository.
+  overrides:
+    parameters:
+      model: llama-cpp/models/ltx2-19b-distilled-q2_k.gguf
+    name: ltx2-gguf
+    backend: llama-cpp
+    template:
+      use_tokenizer_template: true
+    known_usecases:
+      - chat
+    function:
+      grammar:
+        disable: true
+    description: Imported from https://huggingface.co/convertor/ltx2-gguf
+    options:
+      - use_jinja:true
+  files:
+    - filename: llama-cpp/models/ltx2-19b-distilled-q2_k.gguf
+      sha256: cd4e981b3ebb5d27c361be0e04ddda03c64426324ae512451556897cd62c2fec
+      uri: https://huggingface.co/convertor/ltx2-gguf/resolve/main/ltx2-19b-distilled-q2_k.gguf
 - name: "qwen3-vl-reranker-8b"
   url: "github:mudler/LocalAI/gallery/virtual.yaml@master"
   urls:
@@ -3784,7 +3809,7 @@
     - filename: gemma-3-27b-it-mmproj-f16.gguf
       sha256: 54cb61c842fe49ac3c89bc1a614a2778163eb49f3dec2b90ff688b4c0392cb48
       uri: huggingface://lmstudio-community/gemma-3-27b-it-GGUF/mmproj-model-f16.gguf
 - !!merge <<: *gemma3
   name: "gemma-3-12b-it"
   urls:
     - https://ai.google.dev/gemma/docs/core
@@ -3802,7 +3827,7 @@
     - filename: gemma-3-12b-it-mmproj-f16.gguf
       sha256: 30c02d056410848227001830866e0a269fcc28aaf8ca971bded494003de9f5a5
       uri: huggingface://lmstudio-community/gemma-3-12b-it-GGUF/mmproj-model-f16.gguf
 - !!merge <<: *gemma3
   name: "gemma-3-4b-it"
   urls:
     - https://ai.google.dev/gemma/docs/core
@@ -3820,7 +3845,7 @@
     - filename: gemma-3-4b-it-mmproj-f16.gguf
       sha256: 8c0fb064b019a6972856aaae2c7e4792858af3ca4561be2dbf649123ba6c40cb
       uri: huggingface://lmstudio-community/gemma-3-4b-it-GGUF/mmproj-model-f16.gguf
 - !!merge <<: *gemma3
   name: "gemma-3-1b-it"
   urls:
     - https://ai.google.dev/gemma/docs/core
@@ -7038,7 +7063,7 @@
     - smollm
     - chatml
     - cpu
   urls:
     - https://huggingface.co/MaziyarPanahi/SmolLM-1.7B-Instruct-GGUF
     - https://huggingface.co/HuggingFaceTB/SmolLM-1.7B-Instruct
   description: |
@@ -7082,7 +7107,7 @@
     Model developer: Meta
 
     Model Architecture: Llama 3.1 is an auto-regressive language model that uses an optimized transformer architecture. The tuned versions use supervised fine-tuning (SFT) and reinforcement learning with human feedback (RLHF) to align with human preferences for helpfulness and safety.
   urls:
     - https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct
     - https://huggingface.co/MaziyarPanahi/Meta-Llama-3.1-8B-Instruct-GGUF
   tags: