From 16fb9e81bde42b6895a10173fec63e032c05f232 Mon Sep 17 00:00:00 2001
From: Ettore Di Giacinto <mudler@localai.io>
Date: Fri, 11 Sep 2026 22:37:06 +0000
Subject: [PATCH] gallery: apply PR #11923

Assisted-by: localai-org-maint-bot:glm5.2 [gh]
---
 docs/content/features/model-gallery.md | 22 +++---
 gallery/index.yaml                     | 99 ++++++++++++++++++++++++++
 2 files changed, 111 insertions(+), 10 deletions(-)

diff --git a/docs/content/features/model-gallery.md b/docs/content/features/model-gallery.md
index 55344f3cf..8e15df599 100644
--- a/docs/content/features/model-gallery.md
+++ b/docs/content/features/model-gallery.md
@@ -43,25 +43,27 @@ Both views use the same model selection and store the view, search, filter, and
 selection in the URL. Installing from Explore does not move you away from the
 catalog; the entry updates in place when the operation finishes.
 
-## Gemma 4 E4B HauhauCS Aggressive
+## Spark-X2.5-4B
 
-The gallery offers the [HauhauCS Aggressive Gemma 4 E4B model](https://huggingface.co/HauhauCS/Gemma-4-E4B-Uncensored-HauhauCS-Aggressive)
-for text chat and image input through llama.cpp. Both Q4_K_M and Q5_K_M
-builds include the publisher's F16 multimodal projector. They use an 8192-token
-context and the embedded chat template.
-
-Install with automatic variant selection:
+Install Spark-X2.5-4B with automatic selection between its Q4_K_M, Q6_K,
+and Q8_0 GGUF builds:
 
 ```bash
-local-ai models install gemma-4-e4b-hauhaucs-aggressive-q4
+local-ai models install spark-x2.5-4b-q4
 ```
 
-Select Q5_K_M explicitly:
+To select a quantization explicitly:
 
 ```bash
-local-ai models install --variant gemma-4-e4b-hauhaucs-aggressive-q5 gemma-4-e4b-hauhaucs-aggressive-q4
+local-ai models install spark-x2.5-4b-q4 --variant spark-x2.5-4b-q6
 ```
 
+These text-only builds use the llama.cpp backend and the embedded Jinja chat
+template. The gallery defaults to a 32,768-token context to limit memory use.
+The [source model](https://huggingface.co/XHToken/Spark-X2.5-4B) supports up to
+1,048,576 tokens; larger contexts require more memory. Use a current LocalAI
+llama.cpp backend with Spark-X2.5 support (upstream b10828 or later).
+
 ## VRAM and download size estimates
 
 When browsing the gallery or importing a model by URI, LocalAI can show **estimated download size** and **estimated VRAM** for models.
diff --git a/gallery/index.yaml b/gallery/index.yaml
index 899a0bb8c..fcc170f2f 100644
--- a/gallery/index.yaml
+++ b/gallery/index.yaml
@@ -3870,6 +3870,105 @@
     - filename: llama-cpp/mmproj/qwen3.8-27b-gsq-rco/mmproj-Qwen3.8-27B-BF16.gguf
       uri: huggingface://ISTA-DASLab/Qwen3.8-27B-GSQ-RCO-GGUF/mmproj-Qwen3.8-27B-BF16.gguf
       sha256: 13cb7bebccbd04afc8f4090cb949ecf8937cdf7377c5799b1a0c594e7c0d3e16
+- &spark-x2-5-4b
+  name: "spark-x2.5-4b-q4"
+  url: "github:mudler/LocalAI/gallery/virtual.yaml@master"
+  variants:
+    - model: spark-x2.5-4b-q6
+    - model: spark-x2.5-4b-q8
+  urls:
+    - https://huggingface.co/XHToken/Spark-X2.5-4B
+    - https://huggingface.co/abenzerps/Spark-X2.5-4B-GGUF
+  description: |
+    Spark-X2.5-4B is XHToken's 4B text model for conversation, reasoning,
+    coding, and multilingual tasks. This entry uses Q4_K_M GGUF weights;
+    Q6_K and Q8_0 builds are available as variants. All builds use the
+    embedded Jinja chat template and a 32K-token default context.
+  license: "apache-2.0"
+  tags:
+    - llm
+    - gguf
+    - cpu
+    - gpu
+    - reasoning
+    - coding
+    - multilingual
+  last_checked: "2026-09-08"
+  overrides:
+    backend: llama-cpp
+    context_size: 32768
+    known_usecases:
+      - chat
+    options:
+      - use_jinja:true
+    parameters:
+      model: llama-cpp/models/spark-x2.5-4b/Spark-X2.5-4B-Q4_K_M.gguf
+      temperature: 1
+      top_p: 0.95
+      top_k: -1
+      min_p: 0
+      repeat_penalty: 1
+    template:
+      use_tokenizer_template: true
+  files:
+    - filename: llama-cpp/models/spark-x2.5-4b/Spark-X2.5-4B-Q4_K_M.gguf
+      uri: huggingface://abenzerps/Spark-X2.5-4B-GGUF/Spark-X2.5-4B-Q4_K_M.gguf
+      sha256: 7934660bfc5b9bf04be0a0ac6179a1d16e1d4331b448857c86b8b2801b3ef72c
+
+- !!merge <<: *spark-x2-5-4b
+  name: "spark-x2.5-4b-q6"
+  variants: []
+  description: |
+    Spark-X2.5-4B in Q6_K GGUF format, with the embedded Jinja chat
+    template and a 32K-token default context.
+  overrides:
+    backend: llama-cpp
+    context_size: 32768
+    known_usecases:
+      - chat
+    options:
+      - use_jinja:true
+    parameters:
+      model: llama-cpp/models/spark-x2.5-4b/Spark-X2.5-4B-Q6_K.gguf
+      temperature: 1
+      top_p: 0.95
+      top_k: -1
+      min_p: 0
+      repeat_penalty: 1
+    template:
+      use_tokenizer_template: true
+  files:
+    - filename: llama-cpp/models/spark-x2.5-4b/Spark-X2.5-4B-Q6_K.gguf
+      uri: huggingface://abenzerps/Spark-X2.5-4B-GGUF/Spark-X2.5-4B-Q6_K.gguf
+      sha256: 7293e99081e032b30e481c159aa35b3f7d133a746c1096910024ea71fff82246
+
+- !!merge <<: *spark-x2-5-4b
+  name: "spark-x2.5-4b-q8"
+  variants: []
+  description: |
+    Spark-X2.5-4B in Q8_0 GGUF format, with the embedded Jinja chat
+    template and a 32K-token default context.
+  overrides:
+    backend: llama-cpp
+    context_size: 32768
+    known_usecases:
+      - chat
+    options:
+      - use_jinja:true
+    parameters:
+      model: llama-cpp/models/spark-x2.5-4b/Spark-X2.5-4B-Q8_0.gguf
+      temperature: 1
+      top_p: 0.95
+      top_k: -1
+      min_p: 0
+      repeat_penalty: 1
+    template:
+      use_tokenizer_template: true
+  files:
+    - filename: llama-cpp/models/spark-x2.5-4b/Spark-X2.5-4B-Q8_0.gguf
+      uri: huggingface://abenzerps/Spark-X2.5-4B-GGUF/Spark-X2.5-4B-Q8_0.gguf
+      sha256: 58a4fc627cc2b2cbea02f81fb22960938e86bf3e62a2b3ae01c55a678481d46b
+
 - &qwen3-8-9b
   name: "qwen3.8-9b-q4"
   variants: