From 754800bbf3bf24c15cc0190de69439a31632a443 Mon Sep 17 00:00:00 2001
From: localai-org-maint-bot
 <306269227+localai-org-maint-bot@users.noreply.github.com>
Date: Sun, 25 Oct 2026 09:52:02 +0000
Subject: [PATCH] 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

(cherry picked from commit c7cbe18a62a8abe69ae5a1f06fc08a80df4f6e9d, mudler/LocalAI#12707)
Assisted-by: Claude:claude-sonnet-5-5
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
---
 gallery/index.yaml        | 70 +++++++++++++++++++++++++++++++
 gallery/models/index.yaml | 86 +++++++++++++++++++++++++++++++++++++++
 2 files changed, 156 insertions(+)

diff --git a/gallery/index.yaml b/gallery/index.yaml
index 27df5b3bc..948c6b39d 100644
--- a/gallery/index.yaml
+++ b/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: diplodocus-preview-q4
   description: |
diff --git a/gallery/models/index.yaml b/gallery/models/index.yaml
index a4a1af791..629d4ccd3 100644
--- a/gallery/models/index.yaml
+++ b/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: diplodocus-preview-q4
   name: diplodocus-preview-q4