diff --git a/gallery/index.yaml b/gallery/index.yaml
index 9789b820e234..b3c64613c96b 100644
--- a/gallery/index.yaml
+++ b/gallery/index.yaml
@@ -23109,3 +23109,64 @@
     - filename: Qwen3-Nemotron-32B-RLBFF.i1-Q4_K_M.gguf
       sha256: 000e8c65299fc232d1a832f1cae831ceaa16425eccfb7d01702d73e8bd3eafee
       uri: huggingface://mradermacher/Qwen3-Nemotron-32B-RLBFF-i1-GGUF/Qwen3-Nemotron-32B-RLBFF.i1-Q4_K_M.gguf
+- !!merge <<: *sentencentransformers
+  name: "fin-bge-v1"
+  urls:
+    - https://huggingface.co/mradermacher/fin-bge-v1-GGUF
+  description: |
+    **Model Name:** Finance Embeddings BGE v1
+    **Repository:** [Shubham-Mehrotra-PML/fin-bge-v1](https://huggingface.co/Shubham-Mehrotra-PML/fin-bge-v1)
+    **Base Model:** BAAI/bge-base-en-v1.5
+    **License:** Same as base model (Apache 2.0)
+
+    ---
+
+    ### 🏦 **Description**
+    Fine-tuned BGE model specialized for financial domain embeddings. Trained on a comprehensive dataset of financial terms, ratios, and concepts to deliver high-precision semantic similarity for finance-related NLP tasks.
+
+    ### ✨ **Key Features**
+    - **Domain-Specific Performance**: Significantly improved accuracy on financial terms (e.g., *PE Ratio ↔ P/E*, *Stock ↔ Equity*).
+    - **Multi-Objective Training**: Trained with regression, triplet, context, and definition losses for robust embeddings.
+    - **Normalized Embeddings**: Uses L2 normalization for optimal cosine similarity.
+    - **High Precision**: Reduces false positives for unrelated/non-finance terms.
+
+    ### 📊 **Performance Highlights**
+    - **+45.9% improvement** on *Stock ↔ Equity* similarity
+    - **+51.2% improvement** on *PE Ratio ↔ Valuation*
+    - Maintains strong performance on general text while enhancing domain specificity
+
+    ### 🧠 **Architecture**
+    - BERT-based encoder (BGE)
+    - Hidden size: 768 | Layers: 12 | Attention heads: 12
+    - Vocabulary size: 30,522 | Max sequence length: 512
+    - Parameters: ~109.5M
+
+    ### 📌 **Use Cases**
+    - Financial document retrieval
+    - Semantic search in stock reports, earnings calls, and financial news
+    - Matching financial terms and concepts
+    - Building finance-specific QA or recommendation systems
+
+    ### ⚠️ **Limitations**
+    - Optimized for finance; may underperform on general domain tasks
+    - Primarily trained on English financial terminology
+    - Context length capped at 256 tokens for best results
+
+    ---
+
+    **Citation:**
+    ```bibtex
+    @misc{finance-embeddings-bge-v1,
+      title={Finance Embeddings BGE v1: Specialized Financial Domain Embeddings},
+      author={Finance Embeddings Team},
+      year={2025},
+      url={https://huggingface.co/models/fin-bge-v1}
+    }
+    ```
+  overrides:
+    parameters:
+      model: fin-bge-v1.Q8_0.gguf
+  files:
+    - filename: fin-bge-v1.Q8_0.gguf
+      sha256: 30d5292edbefaaad6df42c2b2b22c1e76355a34ea7fd3899df2f287eaf31e9d3
+      uri: huggingface://mradermacher/fin-bge-v1-GGUF/fin-bge-v1.Q8_0.gguf