From da6ef0967d150107bf62888d734bdf6f09f2415c Mon Sep 17 00:00:00 2001 From: Ettore Di Giacinto Date: Tue, 29 Apr 2025 09:48:28 +0200 Subject: [PATCH] chore(model gallery): add qwen3-32b (#5270) Signed-off-by: Ettore Di Giacinto --- gallery/index.yaml | 32 ++++++++++++++++++++++++++++++++ 1 file changed, 32 insertions(+) diff --git a/gallery/index.yaml b/gallery/index.yaml index 9b0e76ea..8974779e 100644 --- a/gallery/index.yaml +++ b/gallery/index.yaml @@ -44,6 +44,38 @@ - filename: Qwen_Qwen3-30B-A3B-Q4_K_M.gguf sha256: a015794bfb1d69cb03dbb86b185fb2b9b339f757df5f8f9dd9ebdab8f6ed5d32 uri: huggingface://bartowski/Qwen_Qwen3-30B-A3B-GGUF/Qwen_Qwen3-30B-A3B-Q4_K_M.gguf +- !!merge <<: *qwen3 + name: "qwen3-32b" + urls: + - https://huggingface.co/Qwen/Qwen3-32B + - https://huggingface.co/bartowski/Qwen_Qwen3-32B-GGUF + description: | + Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models. Built upon extensive training, Qwen3 delivers groundbreaking advancements in reasoning, instruction-following, agent capabilities, and multilingual support, with the following key features: + + Uniquely support of seamless switching between thinking mode (for complex logical reasoning, math, and coding) and non-thinking mode (for efficient, general-purpose dialogue) within single model, ensuring optimal performance across various scenarios. + Significantly enhancement in its reasoning capabilities, surpassing previous QwQ (in thinking mode) and Qwen2.5 instruct models (in non-thinking mode) on mathematics, code generation, and commonsense logical reasoning. + Superior human preference alignment, excelling in creative writing, role-playing, multi-turn dialogues, and instruction following, to deliver a more natural, engaging, and immersive conversational experience. + Expertise in agent capabilities, enabling precise integration with external tools in both thinking and unthinking modes and achieving leading performance among open-source models in complex agent-based tasks. + Support of 100+ languages and dialects with strong capabilities for multilingual instruction following and translation. + + Qwen3-32B has the following features: + + Type: Causal Language Models + Training Stage: Pretraining & Post-training + Number of Parameters: 32.8B + Number of Paramaters (Non-Embedding): 31.2B + Number of Layers: 64 + Number of Attention Heads (GQA): 64 for Q and 8 for KV + Context Length: 32,768 natively and 131,072 tokens with YaRN. + + For more details, including benchmark evaluation, hardware requirements, and inference performance, please refer to our blog, GitHub, and Documentation. + overrides: + parameters: + model: Qwen_Qwen3-32B-Q4_K_M.gguf + files: + - filename: Qwen_Qwen3-32B-Q4_K_M.gguf + sha256: e41ec56ddd376963a116da97506fadfccb50fb402bb6f3cb4be0bc179a582bd6 + uri: huggingface://bartowski/Qwen_Qwen3-32B-GGUF/Qwen_Qwen3-32B-Q4_K_M.gguf - &gemma3 url: "github:mudler/LocalAI/gallery/gemma.yaml@master" name: "gemma-3-27b-it"