diff --git a/gallery/index.yaml b/gallery/index.yaml index 7388eb7e0580..48427c4e7785 100644 --- a/gallery/index.yaml +++ b/gallery/index.yaml @@ -22169,3 +22169,26 @@ - filename: Zirel-2.i1-Q4_K_S.gguf sha256: 9856e987f5f59c874a8fe26ffb2a2c5b7c60b85186131048536b3f1d91a235a6 uri: huggingface://mradermacher/Zirel-2-i1-GGUF/Zirel-2.i1-Q4_K_S.gguf +- !!merge <<: *qwen3 + name: "qwen3-235b-a22b-instruct-2507" + urls: + - https://huggingface.co/John1604/Qwen3-235B-A22B-Instruct-2507-gguf + description: | + **Model Name:** Qwen3-235B-A22B-Instruct-2507 + **Model Type:** Large Language Model (LLM) + **Base Model:** Qwen/Qwen3-235B-A22B-Instruct-2507 (original by Alibaba) + **Size:** 235 billion parameters + **Architecture:** Transformer-based, instruction-tuned for high-quality conversational and reasoning tasks + **License:** Apache 2.0 + **Quantization:** Available in multiple GGUF quantized versions (2-bit to 8-bit) for efficient local inference + **Use Case:** Ideal for advanced reasoning, code generation, dialogue, and complex task execution in local or edge environments + **Note:** This repository hosts quantized GGUF versions of the original Qwen3-235B-A22B-Instruct-2507 model, created and shared by John1604. The base model is authored by Alibaba. + + > 🔍 **Important:** The original, unquantized model is available at: [Qwen/Qwen3-235B-A22B-Instruct-2507](https://huggingface.co/Qwen/Qwen3-235B-A22B-Instruct-2507) — recommended for highest quality and full feature support. + overrides: + parameters: + model: Qwen3-235B-A22B-Instruct-2507-q3_k_m.gguf + files: + - filename: Qwen3-235B-A22B-Instruct-2507-q3_k_m.gguf + sha256: ac894f1a259bb737cdfb093032c4b73d5c4d0f7346a0fbbfe8ed07b6b73e07f3 + uri: huggingface://John1604/Qwen3-235B-A22B-Instruct-2507-gguf/Qwen3-235B-A22B-Instruct-2507-q3_k_m.gguf