From 0348099cdf489a72928a15516682f2d43b12f66f Mon Sep 17 00:00:00 2001
From: localai-org-maint-bot
 <306269227+localai-org-maint-bot@users.noreply.github.com>
Date: Mon, 14 Sep 2026 20:05:41 +0000
Subject: [PATCH] feat(gallery): add Ornith 35B Q5 and Q6 variants

Add the missing intermediate quantizations with the BF16 vision
projector and link them from the existing Q4 entry. Pin the new
artifacts to the publisher revision and document variant selection.

Assisted-by: Codex:gpt-6
---
 docs/content/features/model-gallery.md |  7 +++
 gallery/index.yaml                     | 78 +++++++++++++++++++++++++-
 2 files changed, 83 insertions(+), 2 deletions(-)

diff --git a/docs/content/features/model-gallery.md b/docs/content/features/model-gallery.md
index f0088f583..b83784cb4 100644
--- a/docs/content/features/model-gallery.md
+++ b/docs/content/features/model-gallery.md
@@ -412,6 +412,13 @@ The same option exists on the CLI:
 local-ai models install nanbeige4.1-3b-q4 --variant nanbeige4.1-3b-q8
 ```
 
+Ornith-1.5-35B-A3B offers Q4_K_M, Q5_K_M, Q6_K, and Q8_0 GGUF builds
+with a BF16 vision projector. For example, select Q6_K with:
+
+```bash
+local-ai models install ornith-1.5-35b-a3b-q4 --variant ornith-1.5-35b-a3b-q6
+```
+
 The `install_model` MCP tool takes the same `variant` argument, so an assistant
 managing installs conversationally can pick a build too.
 
diff --git a/gallery/index.yaml b/gallery/index.yaml
index 104827cc3..cd496b98f 100644
--- a/gallery/index.yaml
+++ b/gallery/index.yaml
@@ -3398,6 +3398,8 @@
 - &ornith-1-5-35b-a3b
   name: "ornith-1.5-35b-a3b-q4"
   variants:
+    - model: ornith-1.5-35b-a3b-q5
+    - model: ornith-1.5-35b-a3b-q6
     - model: ornith-1.5-35b-a3b-q8
   url: "github:mudler/LocalAI/gallery/virtual.yaml@master"
   urls:
@@ -3409,8 +3411,8 @@
     tasks, and tool use. It activates about 3B parameters per token and
     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 builds are available as variants.
   license: "mit"
   tags:
     - llm
@@ -3492,6 +3494,78 @@
     - filename: llama-cpp/mmproj/ornith-1.5-35b-a3b/mmproj-BF16.gguf
       uri: huggingface://ornith-ai/Ornith-1.5-35B-A3B-GGUF/mmproj-Ornith-1.5-35B-BF16.gguf
       sha256: 1921a36a85aee56cd2abd27f46701802c9d85a33474792e600df6c3b282a135d
+- !!merge <<: *ornith-1-5-35b-a3b
+  name: "ornith-1.5-35b-a3b-q5"
+  variants: []
+  last_checked: "2026-09-14"
+  description: |
+    Ornith-1.5-35B-A3B 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-1.5-35b-a3b/mmproj-BF16.gguf
+    options:
+      - use_jinja:true
+    parameters:
+      min_p: 0
+      model: llama-cpp/models/ornith-1.5-35b-a3b/Ornith-1.5-35B-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-1.5-35b-a3b/Ornith-1.5-35B-Q5_K_M.gguf
+      uri: https://huggingface.co/ornith-ai/Ornith-1.5-35B-A3B-GGUF/resolve/12393612fd4f730ff5aadc23e9b8f9648aa49ceb/Ornith-1.5-35B-Q5_K_M.gguf
+      sha256: 91df97de5845100e850b4b5ec5ff35695382020b880fad6f7f51787b3a953bd0
+    - filename: llama-cpp/mmproj/ornith-1.5-35b-a3b/mmproj-BF16.gguf
+      uri: https://huggingface.co/ornith-ai/Ornith-1.5-35B-A3B-GGUF/resolve/12393612fd4f730ff5aadc23e9b8f9648aa49ceb/mmproj-Ornith-1.5-35B-BF16.gguf
+      sha256: 1921a36a85aee56cd2abd27f46701802c9d85a33474792e600df6c3b282a135d
+- !!merge <<: *ornith-1-5-35b-a3b
+  name: "ornith-1.5-35b-a3b-q6"
+  variants: []
+  last_checked: "2026-09-14"
+  description: |
+    Ornith-1.5-35B-A3B 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-1.5-35b-a3b/mmproj-BF16.gguf
+    options:
+      - use_jinja:true
+    parameters:
+      min_p: 0
+      model: llama-cpp/models/ornith-1.5-35b-a3b/Ornith-1.5-35B-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-1.5-35b-a3b/Ornith-1.5-35B-Q6_K.gguf
+      uri: https://huggingface.co/ornith-ai/Ornith-1.5-35B-A3B-GGUF/resolve/12393612fd4f730ff5aadc23e9b8f9648aa49ceb/Ornith-1.5-35B-Q6_K.gguf
+      sha256: 15d4658bbfc9c6034621729c15bbb50662c82b32a7ddd9624a1e545a74bdbb4b
+    - filename: llama-cpp/mmproj/ornith-1.5-35b-a3b/mmproj-BF16.gguf
+      uri: https://huggingface.co/ornith-ai/Ornith-1.5-35B-A3B-GGUF/resolve/12393612fd4f730ff5aadc23e9b8f9648aa49ceb/mmproj-Ornith-1.5-35B-BF16.gguf
+      sha256: 1921a36a85aee56cd2abd27f46701802c9d85a33474792e600df6c3b282a135d
 - &nex-n2-5-mini
   name: "nex-n2.5-mini-q4"
   variants: