Llama.cpp on Asanilo's Blog https://www.asanilo.top/tags/llama.cpp/ Recent content in Llama.cpp on Asanilo's Blog Hugo -- gohugo.io zh-cn © 2026 Asanilo Fri, 15 May 2026 00:00:00 +0000 GGUF 模型文件到底是什么：从使用者视角理解本地 LLM https://www.asanilo.top/posts/%E6%9C%AC%E5%9C%B0%E5%A4%A7%E6%A8%A1%E5%9E%8B/gguf-model-format-explained/ Fri, 15 May 2026 00:00:00 +0000 https://www.asanilo.top/posts/%E6%9C%AC%E5%9C%B0%E5%A4%A7%E6%A8%A1%E5%9E%8B/gguf-model-format-explained/ MTP神力！RTX 4060 8GB 也能跑 26B 模型？ https://www.asanilo.top/posts/%E6%9C%AC%E5%9C%B0%E5%A4%A7%E6%A8%A1%E5%9E%8B/rtx4060-gemma4-mtp-local-llm/ Fri, 15 May 2026 00:00:00 +0000 https://www.asanilo.top/posts/%E6%9C%AC%E5%9C%B0%E5%A4%A7%E6%A8%A1%E5%9E%8B/rtx4060-gemma4-mtp-local-llm/ Q4_K_M 这类量化格式是什么意思：怎么影响速度和质量 https://www.asanilo.top/posts/%E6%9C%AC%E5%9C%B0%E5%A4%A7%E6%A8%A1%E5%9E%8B/quantization-q4km-explained/ Fri, 15 May 2026 00:00:00 +0000 https://www.asanilo.top/posts/%E6%9C%AC%E5%9C%B0%E5%A4%A7%E6%A8%A1%E5%9E%8B/quantization-q4km-explained/ 本地大模型部署工程清单：模型、推理框架、显存、上下文、速度 https://www.asanilo.top/posts/%E6%9C%AC%E5%9C%B0%E5%A4%A7%E6%A8%A1%E5%9E%8B/local-llm-deployment-checklist/ Fri, 15 May 2026 00:00:00 +0000 https://www.asanilo.top/posts/%E6%9C%AC%E5%9C%B0%E5%A4%A7%E6%A8%A1%E5%9E%8B/local-llm-deployment-checklist/ 用 llama.cpp server 搭一个本地 OpenAI-compatible API https://www.asanilo.top/posts/%E6%9C%AC%E5%9C%B0%E5%A4%A7%E6%A8%A1%E5%9E%8B/llama-cpp-server-openai-api/ Fri, 15 May 2026 00:00:00 +0000 https://www.asanilo.top/posts/%E6%9C%AC%E5%9C%B0%E5%A4%A7%E6%A8%A1%E5%9E%8B/llama-cpp-server-openai-api/