From 85973f856529c70ae0379043cb019fb13fdc103b Mon Sep 17 00:00:00 2001 From: mudler <2420543+mudler@users.noreply.github.com> Date: Tue, 14 Apr 2026 06:45:58 +0000 Subject: [PATCH] chore(model gallery): :robot: add new models via gallery agent Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> --- gallery/index.yaml | 55 ++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 55 insertions(+) diff --git a/gallery/index.yaml b/gallery/index.yaml index 3c62aae10cd6..eba73c6c17cb 100644 --- a/gallery/index.yaml +++ b/gallery/index.yaml @@ -1,4 +1,59 @@ --- +- name: "gemma-4-26b-a4b-it" + url: "github:mudler/LocalAI/gallery/virtual.yaml@master" + urls: + - https://huggingface.co/unsloth/gemma-4-26B-A4B-it-GGUF + description: | + + Hugging Face | + GitHub | + Launch Blog | + Documentation + + License: Apache 2.0 | Authors: Google DeepMind + + Gemma is a family of open models built by Google DeepMind. Gemma 4 models are multimodal, handling text and image input (with audio supported on small models) and generating text output. This release includes open-weights models in both pre-trained and instruction-tuned variants. Gemma 4 features a context window of up to 256K tokens and maintains multilingual support in over 140 languages. + + Featuring both Dense and Mixture-of-Experts (MoE) architectures, Gemma 4 is well-suited for tasks like text generation, coding, and reasoning. The models are available in four distinct sizes: **E2B**, **E4B**, **26B A4B**, and **31B**. Their diverse sizes make them deployable in environments ranging from high-end phones to laptops and servers, democratizing access to state-of-the-art AI. + + Gemma 4 introduces key **capability and architectural advancements**: + + * **Reasoning** – All models in the family are designed as highly capable reasoners, with configurable thinking modes. + + ... + license: "apache-2.0" + tags: + - llm + - gguf + - gemma + icon: https://ai.google.dev/gemma/images/gemma4_banner.png + overrides: + backend: llama-cpp + function: + automatic_tool_parsing_fallback: true + grammar: + disable: true + known_usecases: + - chat + mmproj: llama-cpp/mmproj/gemma-4-26B-A4B-it-GGUF/mmproj-F32.gguf + options: + - use_jinja:true + parameters: + min_p: 0 + model: llama-cpp/models/gemma-4-26B-A4B-it-GGUF/gemma-4-26B-A4B-it-UD-Q4_K_M.gguf + repeat_penalty: 1 + temperature: 1 + top_k: 64 + top_p: 0.95 + template: + use_tokenizer_template: true + files: + - filename: llama-cpp/models/gemma-4-26B-A4B-it-GGUF/gemma-4-26B-A4B-it-UD-Q4_K_M.gguf + sha256: b8707e57f676d8dd1b80f623b45200cc92e6966b0e95275e606f412095a49fde + uri: https://huggingface.co/unsloth/gemma-4-26B-A4B-it-GGUF/resolve/main/gemma-4-26B-A4B-it-UD-Q4_K_M.gguf + - filename: llama-cpp/mmproj/gemma-4-26B-A4B-it-GGUF/mmproj-F32.gguf + sha256: ce12ca17e5f479ff292cd66817960e4d3f1b09671f744e415c98a55d7725c9ed + uri: https://huggingface.co/unsloth/gemma-4-26B-A4B-it-GGUF/resolve/main/mmproj-F32.gguf - name: "gemma-4-26b-a4b-it-apex" url: "github:mudler/LocalAI/gallery/virtual.yaml@master" urls: