From ea51567b89ec90e394a9737b5a6c9dce0d6f90a1 Mon Sep 17 00:00:00 2001
From: "LocalAI [bot]" <139863280+localai-bot@users.noreply.github.com>
Date: Fri, 23 Jan 2026 08:19:39 +0100
Subject: [PATCH] chore(model gallery): :robot: add 1 new models via gallery
 agent (#8170)

chore(model gallery): :robot: add new models via gallery agent

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
---
 gallery/index.yaml | 32 ++++++++++++++++++++++++++++++++
 1 file changed, 32 insertions(+)

diff --git a/gallery/index.yaml b/gallery/index.yaml
index 0189b2d63..bea33dfa5 100644
--- a/gallery/index.yaml
+++ b/gallery/index.yaml
@@ -1,4 +1,36 @@
 ---
+- name: "huihui-glm-4.7-flash-abliterated-i1"
+  url: "github:mudler/LocalAI/gallery/virtual.yaml@master"
+  urls:
+    - https://huggingface.co/mradermacher/Huihui-GLM-4.7-Flash-abliterated-i1-GGUF
+  description: |
+    The model is a quantized version of **huihui-ai/Huihui-GLM-4.7-Flash-abliterated**, optimized for efficiency and deployment. It uses GGUF files with various quantization levels (e.g., IQ1_M, IQ2_XXS, Q4_K_M) and is designed for tasks requiring low-resource deployment. Key features include:
+      - **Base Model**: Huihui-GLM-4.7-Flash-abliterated (unmodified, original model).
+      - **Quantization**: Supports IQ1_M to Q4_K_M, balancing accuracy and efficiency.
+      - **Use Cases**: Suitable for applications needing lightweight inference, such as edge devices or resource-constrained environments.
+      - **Downloads**: Available in GGUF format with varying quality and size (e.g., 0.2GB to 18.2GB).
+      - **Tags**: Abliterated, uncensored, and optimized for specific tasks.
+
+    This model is a modified version of the original GLM-4.7, tailored for deployment with quantized weights.
+  overrides:
+    parameters:
+      model: llama-cpp/models/Huihui-GLM-4.7-Flash-abliterated.i1-Q4_K_M.gguf
+    name: Huihui-GLM-4.7-Flash-abliterated-i1-GGUF
+    backend: llama-cpp
+    template:
+      use_tokenizer_template: true
+    known_usecases:
+      - chat
+    function:
+      grammar:
+        disable: true
+    description: Imported from https://huggingface.co/mradermacher/Huihui-GLM-4.7-Flash-abliterated-i1-GGUF
+    options:
+      - use_jinja:true
+  files:
+    - filename: llama-cpp/models/Huihui-GLM-4.7-Flash-abliterated.i1-Q4_K_M.gguf
+      sha256: 2ec5fcf2aa882c0c55fc67a35ea7ed50c24016bc4a8a4ceacfcea103dc2f1cb8
+      uri: https://huggingface.co/mradermacher/Huihui-GLM-4.7-Flash-abliterated-i1-GGUF/resolve/main/Huihui-GLM-4.7-Flash-abliterated.i1-Q4_K_M.gguf
 - name: "mox-small-1-i1"
   url: "github:mudler/LocalAI/gallery/virtual.yaml@master"
   urls: