feat(gallery): add Qwen3.5 Artemis 0.8B variants

Add text-only Q4 and Q5 builds for llama.cpp with pinned downloads.
Group the builds as variants and document their supported capabilities.

Assisted-by: Codex:gpt-6

docs/content/features/model-gallery.md

@@ -1112,3 +1112,17 @@ is still running is reported as queued until the installer picks it up:
 A job ID is queryable from the moment `/models/apply` returns it, so a `404`/`500`
 from this endpoint means the ID is genuinely unknown rather than merely waiting
 its turn.
+
+## Qwen3.5 0.8B Artemis
+
+Install `qwen3.5-0.8b-artemis-q5` for TurinTech’s Q5_K_M build. The smaller
+Q4_K_M build is available as `qwen3.5-0.8b-artemis-q4` through variant selection.
+Both use llama.cpp, the embedded chat template, and an 8192-token context.
+These text-only builds support chat, reasoning, and tool use; they omit the
+vision encoder and MTP layer. Applications must execute any requested tools.
+
+```sh
+local-ai models install qwen3.5-0.8b-artemis-q5
+```
+
+See the [publisher’s model card](https://huggingface.co/turintech/Qwen3.5-0.8B-Artemis-GGUF) for quantization details.

gallery/index.yaml

@@ -3,6 +3,76 @@
 # written by scripts/models/cmd/modelcatalog and stays only so releases before
 # the cutover keep working. CI fails when it differs from the generated copy:
 #   go run ./scripts/models/cmd/modelcatalog --library gallery/models/index.yaml --out gallery/index.yaml
+- url: github:mudler/LocalAI/gallery/virtual.yaml@master
+  name: qwen3.5-0.8b-artemis-q5
+  description: |
+    TurinTech Artemis Q5_K_M quantization of Qwen3.5 0.8B for text chat,
+    reasoning, and tool use. This text-only build omits the vision encoder
+    and MTP layer. Uses the embedded chat template and an 8192-token context.
+  license: apache-2.0
+  urls:
+    - https://huggingface.co/Qwen/Qwen3.5-0.8B
+    - https://huggingface.co/turintech/Qwen3.5-0.8B-Artemis-GGUF
+  tags:
+    - llm
+    - gguf
+    - cpu
+    - gpu
+    - qwen
+  files:
+    - filename: Qwen3.5-0.8B-Artemis-Q5_K_M.gguf
+      sha256: 3b782856b66f61b4494b346ad8ff3e91a0d4c294ecedd1797f1855a078abbd05
+      uri: https://huggingface.co/turintech/Qwen3.5-0.8B-Artemis-GGUF/resolve/98eb257fe3b2b165e5b4f0ecfa9f127a17823e06/Qwen3.5-0.8B-Artemis-Q5_K_M.gguf
+  overrides:
+    backend: llama-cpp
+    context_size: 8192
+    function:
+      grammar:
+        disable: true
+    known_usecases:
+      - chat
+    options:
+      - use_jinja:true
+    parameters:
+      model: Qwen3.5-0.8B-Artemis-Q5_K_M.gguf
+    template:
+      use_tokenizer_template: true
+  variants:
+    - model: qwen3.5-0.8b-artemis-q4
+- url: github:mudler/LocalAI/gallery/virtual.yaml@master
+  name: qwen3.5-0.8b-artemis-q4
+  description: |
+    TurinTech Artemis Q4_K_M quantization of Qwen3.5 0.8B for text chat,
+    reasoning, and tool use. This text-only build omits the vision encoder
+    and MTP layer. Uses the embedded chat template and an 8192-token context.
+  license: apache-2.0
+  urls:
+    - https://huggingface.co/Qwen/Qwen3.5-0.8B
+    - https://huggingface.co/turintech/Qwen3.5-0.8B-Artemis-GGUF
+  tags:
+    - llm
+    - gguf
+    - cpu
+    - gpu
+    - qwen
+  files:
+    - filename: Qwen3.5-0.8B-Artemis-Q4_K_M.gguf
+      sha256: 01e0651f0fc5d0f9a3d1a68166fbdf12ab4d3bb135b3d725d694f42becfaa5a4
+      uri: https://huggingface.co/turintech/Qwen3.5-0.8B-Artemis-GGUF/resolve/98eb257fe3b2b165e5b4f0ecfa9f127a17823e06/Qwen3.5-0.8B-Artemis-Q4_K_M.gguf
+  overrides:
+    backend: llama-cpp
+    context_size: 8192
+    function:
+      grammar:
+        disable: true
+    known_usecases:
+      - chat
+    options:
+      - use_jinja:true
+    parameters:
+      model: Qwen3.5-0.8B-Artemis-Q4_K_M.gguf
+    template:
+      use_tokenizer_template: true
 - url: github:mudler/LocalAI/gallery/virtual.yaml@master
   name: adavar-3b-q4
   description: |

gallery/models/index.yaml

@@ -4,6 +4,92 @@
 # changes and never edit it by hand. CI fails when it is stale. A build from
 # master reads it as the default model source; a tagged build reads the gallery
 # until the release cutover.
+- kind: model
+  id: qwen3.5-0.8b-artemis-q5
+  name: qwen3.5-0.8b-artemis-q5
+  version: 0.0.0-gallery.536455f1d8a6
+  description: |
+    TurinTech Artemis Q5_K_M quantization of Qwen3.5 0.8B for text chat,
+    reasoning, and tool use. This text-only build omits the vision encoder
+    and MTP layer. Uses the embedded chat template and an 8192-token context.
+  license: apache-2.0
+  urls:
+    - https://huggingface.co/Qwen/Qwen3.5-0.8B
+    - https://huggingface.co/turintech/Qwen3.5-0.8B-Artemis-GGUF
+  tags:
+    - llm
+    - gguf
+    - cpu
+    - gpu
+    - qwen
+  channel: gallery
+  policy:
+    requireSignature: false
+  schemaVersion: 1
+  model:
+    url: github:mudler/LocalAI/gallery/virtual.yaml@master
+    files:
+      - filename: Qwen3.5-0.8B-Artemis-Q5_K_M.gguf
+        sha256: 3b782856b66f61b4494b346ad8ff3e91a0d4c294ecedd1797f1855a078abbd05
+        uri: https://huggingface.co/turintech/Qwen3.5-0.8B-Artemis-GGUF/resolve/98eb257fe3b2b165e5b4f0ecfa9f127a17823e06/Qwen3.5-0.8B-Artemis-Q5_K_M.gguf
+    overrides:
+      backend: llama-cpp
+      context_size: 8192
+      function:
+        grammar:
+          disable: true
+      known_usecases:
+        - chat
+      options:
+        - use_jinja:true
+      parameters:
+        model: Qwen3.5-0.8B-Artemis-Q5_K_M.gguf
+      template:
+        use_tokenizer_template: true
+    variants:
+      - model: qwen3.5-0.8b-artemis-q4
+- kind: model
+  id: qwen3.5-0.8b-artemis-q4
+  name: qwen3.5-0.8b-artemis-q4
+  version: 0.0.0-gallery.b7476e18bdd7
+  description: |
+    TurinTech Artemis Q4_K_M quantization of Qwen3.5 0.8B for text chat,
+    reasoning, and tool use. This text-only build omits the vision encoder
+    and MTP layer. Uses the embedded chat template and an 8192-token context.
+  license: apache-2.0
+  urls:
+    - https://huggingface.co/Qwen/Qwen3.5-0.8B
+    - https://huggingface.co/turintech/Qwen3.5-0.8B-Artemis-GGUF
+  tags:
+    - llm
+    - gguf
+    - cpu
+    - gpu
+    - qwen
+  channel: gallery
+  policy:
+    requireSignature: false
+  schemaVersion: 1
+  model:
+    url: github:mudler/LocalAI/gallery/virtual.yaml@master
+    files:
+      - filename: Qwen3.5-0.8B-Artemis-Q4_K_M.gguf
+        sha256: 01e0651f0fc5d0f9a3d1a68166fbdf12ab4d3bb135b3d725d694f42becfaa5a4
+        uri: https://huggingface.co/turintech/Qwen3.5-0.8B-Artemis-GGUF/resolve/98eb257fe3b2b165e5b4f0ecfa9f127a17823e06/Qwen3.5-0.8B-Artemis-Q4_K_M.gguf
+    overrides:
+      backend: llama-cpp
+      context_size: 8192
+      function:
+        grammar:
+          disable: true
+      known_usecases:
+        - chat
+      options:
+        - use_jinja:true
+      parameters:
+        model: Qwen3.5-0.8B-Artemis-Q4_K_M.gguf
+      template:
+        use_tokenizer_template: true
 - kind: model
   id: adavar-3b-q4
   name: adavar-3b-q4