From 0999b618bcca97ebfd88d566d68be4075e45e71f Mon Sep 17 00:00:00 2001 From: Ettore Di Giacinto Date: Thu, 7 Aug 2025 09:04:49 +0200 Subject: [PATCH] chore(model gallery): add qwen_qwen3-4b-instruct-2507 Signed-off-by: Ettore Di Giacinto --- gallery/index.yaml | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) diff --git a/gallery/index.yaml b/gallery/index.yaml index 04be07934ef2..fc4f5ff9414d 100644 --- a/gallery/index.yaml +++ b/gallery/index.yaml @@ -2095,6 +2095,25 @@ - filename: Qwen_Qwen3-30B-A3B-Thinking-2507-Q4_K_M.gguf sha256: 1359aa08e2f2dfe7ce4b5ff88c4c996e6494c9d916b1ebacd214bb74bbd5a9db uri: huggingface://bartowski/Qwen_Qwen3-30B-A3B-Thinking-2507-GGUF/Qwen_Qwen3-30B-A3B-Thinking-2507-Q4_K_M.gguf +- !!merge <<: *qwen3 + name: "qwen_qwen3-4b-instruct-2507" + urls: + - https://huggingface.co/bartowski/Qwen_Qwen3-4B-Instruct-2507-GGUF + - https://huggingface.co/Qwen/Qwen3-4B-Instruct-2507 + description: | + We introduce the updated version of the Qwen3-4B non-thinking mode, named Qwen3-4B-Instruct-2507, featuring the following key enhancements: + + Significant improvements in general capabilities, including instruction following, logical reasoning, text comprehension, mathematics, science, coding and tool usage. + Substantial gains in long-tail knowledge coverage across multiple languages. + Markedly better alignment with user preferences in subjective and open-ended tasks, enabling more helpful responses and higher-quality text generation. + Enhanced capabilities in 256K long-context understanding. + overrides: + parameters: + model: Qwen_Qwen3-4B-Instruct-2507-Q8_0.gguf + files: + - filename: Qwen_Qwen3-4B-Instruct-2507-Q8_0.gguf + sha256: 260b5b5b6ad73e44df81a43ea1f5c11c37007b6bac18eb3cd2016e8667c19662 + uri: huggingface://bartowski/Qwen_Qwen3-4B-Instruct-2507-GGUF/Qwen_Qwen3-4B-Instruct-2507-Q8_0.gguf - &gemma3 url: "github:mudler/LocalAI/gallery/gemma.yaml@master" name: "gemma-3-27b-it"