跨平台LLM推理服务器，原生支持Qwen、Gemma、Mistral、LLaMa等主流架构，一键Docker部署并集成HuggingFace与S3/GCS存储
Article URL: https://zml.ai/posts/llmd/ Comments URL: https://news.ycombinator.com/item?id=48829412 Points: 3 # Comments: 2
手把手教你用 "gemma-trainer" 在本地微调 Gemma 4 E2B 模型，快速上手大模型定制！
Remember back in May when I introduced the gemma-skills repository? It's been rewarding to see how many of you have used my previous post to streamlin…
从Claude到开源模型：研究发现LLM内部存在类似人类心理结构的情绪向量，并揭示其因果影响行为。
arXiv:2606.26987v1 Announce Type: cross Abstract: Recent work identified emotion vectors in Claude Sonnet 4.5, which are internal representations that…
真实伤口图像上评估医学视觉语言模型与通用聊天机器人，HuluMed、MedGemma、Gemma 3、ChatGPT Plus、Claude Pro谁更强？
arXiv:2606.20723v1 Announce Type: new Abstract: Chronic wound assessment remains a clinically challenging task that requires accurate interpretation o…
一行命令部署任何LLM，Flama让Gemma 4等模型在Apple Silicon上极速运行
Flama 2.0 brings first-class support for generative AI: downloading, packaging, and serving large language models (LLMs) is now as simple as running a…
Gemma 4赋能《Solstice Eternal》，用AI生成创意与强化叙事，打造沉浸式冒险体验。
This is a submission for the Gemma 4 Challenge: Build with Gemma 4 What I Built Solstice Eternal – AI Adventure Game Solstice Eternal is an interactiv…
编辑单个神经元，就能修复大模型在长枚举任务中的重复循环崩溃？这项研究揭示了 Gemma 4 模型的深层问题与解法。
arXiv:2606.13705v1 Announce Type: cross Abstract: Yes. Can it cure doom loops? Probably not. The Gemma 4 instruction-tuned models share a reproducible…
基于文本扩散的开放AI模型，本地推理速度提升4倍，高效处理文本生成任务
IT之家 6 月 11 日消息，谷歌今天（6 月 11 日）发布公告，宣布推出 DiffusionGemma，是基于文本扩散机制的开放 AI 模型， 相比较自回归模型在本地推理速度上提升了 4 倍。 IT之家注：自回归模型（Autoregressive Model）是当前主流的大语言模型架构（如 G…
用Ollama配合QAT量化，10GB显存笔记本也能跑12B的Gemma 4大模型，内存仅需6.7GB。
This stack uses Ollama with Gemma 4 QAT to run a 12B model on a 10GB VRAM laptop GPU. The latest Gemma 4 QAT checkpoints reduce memory usage and enabl…
一种实用的一次性剪枝方法，同时支持稀疏与密集GEMM运算，显著降低LLM推理成本。
arXiv:2606.10445v1 Announce Type: new Abstract: Semi-structured 2:4 sparsity is widely supported by modern accelerators, providing up to a 2x theoreti…
本地运行Gemma4实现人-LLM-Web交互，Bonsai项目让AI操作浏览器门槛大降
Article URL: https://drive.google.com/drive/folders/1QsdOvsBKIavXDhwikouzQMOc8H_94bQd Comments URL: https://news.ycombinator.com/item?id=48461245 Poin…
从Qwen换到Gemma 4 E4B：本地大模型的新选择，性能与易用性如何？
Article URL: https://digg.com/ai/bfr4bqhh Comments URL: https://news.ycombinator.com/item?id=48437537 Points: 2 # Comments: 0
专为Apple Metal优化的GEMM内核生成器开源发布，支持自定义tile、warp、数据类型与激活函数，加速Metal计算性能。
Released mCemm a GEMM (General Matrix Multiply) kernel generator for Apple Metal which generates optimized Metal shaders with configurable tile sizes,…
Google 最新多模态模型 Gemma 4 12B 无需编码器即可本地运行，开源灵活且高效。
Run multimodal AI locally with an encoder-free architecture Discussion | Link
谷歌推出Coral Board单板计算机，1 TOPS算力即可本地运行Gemma 3模型，专为边缘AI场景设计。
IT之家 5 月 29 日消息，在 2026 年 I/O 开发者大会期间，谷歌推出 Coral Board， 是可以本地运行 Gemma 3 模型的小型单板计算机。 Coral Board 最大的亮点，在于搭载 Coral NPU，该机器学习单元由 Google Research 研发，基于 RIS…
本地运行Gemma、Granite、Qwen三款大模型，趣味对比谁更会回答匹萨问题
Article URL: https://ekorbia.com/blog/2026-05-25-fun-local-llm-comparisons Comments URL: https://news.ycombinator.com/item?id=48308210 Points: 3 # Com…
揭秘长上下文推理的内存陷阱：即便模型量化后塞入显存，注意力KV缓存也可能比模型本身更吃内存。
A raw, developer-first look at Google’s new open-weight Gemma 4 family—featuring a hands-on local Python setup, a comparison of the 2B, 9B, and 31B va…
浏览器内虚拟机上，AI用Gemma模型生成x86_64汇编和eBPF代码直接操作/dev/fb0绘制分形，30秒启动工作环境，展示AI编码沙箱的底层能力。
Article URL: https://zozo123.github.io/wolfram-fb0/ Comments URL: https://news.ycombinator.com/item?id=48257102 Points: 1 # Comments: 0
单GPU微调Gemma 4情感数据集，Apache 2.0开源让商用无门槛。
This is a submission for the Gemma 4 Challenge: Write About Gemma 4 When Google dropped Gemma 4 in April 2025, my first reaction was skepticism. We ha…
非程序员教师利用Gemma 4打造全离线Android App，将混乱语音自动转为整洁文字，专为ADD人群设计。
This is a submission for the Gemma 4 Challenge: Build with Gemma 4 What I Built I'm Mark. I'm a middle-school teacher, and I'm not a coder. A few time…