szzzh

Currently, there is no support for gguf-based ollama-ipex-llm inference in jina-embeddings-v3 or jina-reranker-v2-base-multilingual. Do we have any plans to add this support in the future? ollama-ipex-llm [ollama-ipex-llm-2.2.0-ubuntu.tgz](https://github.com/intel/ipex-llm/releases/download/v2.2.0/ollama-ipex-llm-2.2.0-ubuntu.tgz) model url: embedding...

No Qwen2.5-VL-3B-Instruct gguf support. Do we have plan to support? https://github.com/intel/ipex-llm/releases/tag/v2.2.0-nightly [llama-cpp-ipex-llm-2.2.0b20250313-ubuntu-core.tgz](https://github.com/intel/ipex-llm/releases/download/v2.2.0-nightly/llama-cpp-ipex-llm-2.2.0b20250313-ubuntu-core.tgz) model url: https://hf-mirror.com/RzZ/Qwen2.5-VL-3B-GGUF

ultra5 125H/ultra7 255H 在不同版本ollama/llama-cpp上的推理速度差异较大

3

ultra5 125H/ultra7 255H 在不同版本ollama/llama-cpp上的推理速度差异较大 6011: Ultra7 125H 6011 pro: Ultra7 255H 对比相同的qwen2.5-1.5b模型，ollama / llama-cpp 推理速度相差50%以上