feat(gallery): add Ornith 9B Q5 and Q6 variants

Offer intermediate GGUF sizes with the existing vision projector and
llama.cpp settings. Pin downloads and document explicit Q6 selection.

Assisted-by: Codex:gpt-6

docs/content/features/model-gallery.md

@@ -193,6 +193,12 @@ where:
 
 ### Model variants
 
+Ornith 1.5 9B offers Q4_K_M, Q5_K_M, Q6_K, and Q8_0 GGUF builds with a shared BF16 vision projector. To select Q6_K explicitly:
+
+```bash
+local-ai models install ornith-1.5-9b-q4 --variant ornith-1.5-9b-q6
+```
+
 Some gallery entries offer several builds of the same model: different
 quantizations, or the same weights served by a different engine. Such an entry
 carries a `variants` list, and installing it normally lets LocalAI choose:

gallery/index.yaml

@@ -2047,6 +2047,8 @@
 - &ornith-1-5-9b
   name: "ornith-1.5-9b-q4"
   variants:
+    - model: ornith-1.5-9b-q5
+    - model: ornith-1.5-9b-q6
     - model: ornith-1.5-9b-q8
   url: "github:mudler/LocalAI/gallery/virtual.yaml@master"
   urls:
@@ -2057,8 +2059,8 @@
     agentic coding, reasoning, repository-level software tasks, and tool use.
     It supports text and image input with a context window of 262K tokens.
 
-    This default entry uses the Q4_K_M GGUF and BF16 vision projector. A
-    higher-quality Q8_0 model is available as a variant.
+    This default entry uses the Q4_K_M GGUF and BF16 vision projector.
+    Q5_K_M, Q6_K, and Q8_0 models are available as variants.
   license: "mit"
   tags:
     - llm
@@ -2104,6 +2106,78 @@
     - filename: llama-cpp/mmproj/ornith-1.5-9b/mmproj-BF16.gguf
       uri: huggingface://ornith-ai/Ornith-1.5-9B-GGUF/mmproj-Ornith-1.5-9B-BF16.gguf
       sha256: 626f9f90627402a6bf4a999111d0fbd69b5fcca7aa8ba089d69e5f10e8858e1d
+- !!merge <<: *ornith-1-5-9b
+  name: "ornith-1.5-9b-q5"
+  variants: []
+  last_checked: "2026-09-09"
+  description: |
+    Ornith-1.5-9B in the Q5_K_M GGUF format, with the shared BF16
+    vision projector for multimodal prompts.
+  overrides:
+    backend: llama-cpp
+    context_size: 262144
+    function:
+      automatic_tool_parsing_fallback: true
+      grammar:
+        disable: true
+    known_usecases:
+      - chat
+      - vision
+    mmproj: llama-cpp/mmproj/ornith-1.5-9b/mmproj-BF16.gguf
+    options:
+      - use_jinja:true
+    parameters:
+      min_p: 0
+      model: llama-cpp/models/ornith-1.5-9b/Ornith-1.5-9B-Q5_K_M.gguf
+      repeat_penalty: 1
+      temperature: 0.6
+      top_k: 20
+      top_p: 0.95
+    template:
+      use_tokenizer_template: true
+  files:
+    - filename: llama-cpp/models/ornith-1.5-9b/Ornith-1.5-9B-Q5_K_M.gguf
+      uri: https://huggingface.co/ornith-ai/Ornith-1.5-9B-GGUF/resolve/abdd624b12ebf020b767fff532ff44fe552b28c3/Ornith-1.5-9B-Q5_K_M.gguf
+      sha256: e4d9634a3b6546a5c00a8680568fe1125f6c98c704ee51ae52ba07650fb4247d
+    - filename: llama-cpp/mmproj/ornith-1.5-9b/mmproj-BF16.gguf
+      uri: https://huggingface.co/ornith-ai/Ornith-1.5-9B-GGUF/resolve/abdd624b12ebf020b767fff532ff44fe552b28c3/mmproj-Ornith-1.5-9B-BF16.gguf
+      sha256: 626f9f90627402a6bf4a999111d0fbd69b5fcca7aa8ba089d69e5f10e8858e1d
+- !!merge <<: *ornith-1-5-9b
+  name: "ornith-1.5-9b-q6"
+  variants: []
+  last_checked: "2026-09-09"
+  description: |
+    Ornith-1.5-9B in the Q6_K GGUF format, with the shared BF16
+    vision projector for multimodal prompts.
+  overrides:
+    backend: llama-cpp
+    context_size: 262144
+    function:
+      automatic_tool_parsing_fallback: true
+      grammar:
+        disable: true
+    known_usecases:
+      - chat
+      - vision
+    mmproj: llama-cpp/mmproj/ornith-1.5-9b/mmproj-BF16.gguf
+    options:
+      - use_jinja:true
+    parameters:
+      min_p: 0
+      model: llama-cpp/models/ornith-1.5-9b/Ornith-1.5-9B-Q6_K.gguf
+      repeat_penalty: 1
+      temperature: 0.6
+      top_k: 20
+      top_p: 0.95
+    template:
+      use_tokenizer_template: true
+  files:
+    - filename: llama-cpp/models/ornith-1.5-9b/Ornith-1.5-9B-Q6_K.gguf
+      uri: https://huggingface.co/ornith-ai/Ornith-1.5-9B-GGUF/resolve/abdd624b12ebf020b767fff532ff44fe552b28c3/Ornith-1.5-9B-Q6_K.gguf
+      sha256: b6f76e74f86245b3caee014b797c10dca931c4dfdaabfb134eab655f81e4154a
+    - filename: llama-cpp/mmproj/ornith-1.5-9b/mmproj-BF16.gguf
+      uri: https://huggingface.co/ornith-ai/Ornith-1.5-9B-GGUF/resolve/abdd624b12ebf020b767fff532ff44fe552b28c3/mmproj-Ornith-1.5-9B-BF16.gguf
+      sha256: 626f9f90627402a6bf4a999111d0fbd69b5fcca7aa8ba089d69e5f10e8858e1d
 - !!merge <<: *ornith-1-5-9b
   name: "ornith-1.5-9b-q8"
   variants: []