为什么你该停止使用 Ollama

[catazshadow]

原文：
https://sleepingrobots.com/dreams/stop-using-ollama/

“Ollama wrapped that work in a nice CLI, raised VC money on the back of it, spent over a year refusing to credit it, forked it badly, shipped a closed-source app alongside it, and then pivoted the whole thing toward cloud services. At every decision point where they could have been good open-source citizens, they chose the path that made them look more self-sufficient to investors.”

总之就是开源小偷，还尝试锁死用户

原文建议用这些：

llama.cpp is the engine. It has an OpenAI-compatible API server (llama-server), a built-in web UI, full control over context windows and sampling parameters, and consistently better throughput than Ollama. In February 2026, Gerganov’s ggml.ai joined Hugging Face to ensure the long-term sustainability of the project. It’s truly community-driven, MIT-licensed, and under active development with 450+ contributors.

llama-swap handles multi-model orchestration, loading, unloading, and hot-swapping models on demand behind a single API endpoint. Pair it with LiteLLM and you get a unified OpenAI-compatible proxy that routes across multiple backends with proper model aliasing.

LM Studio gives you a GUI if that’s what you want. It uses llama.cpp under the hood, exposes all the knobs, and supports any GGUF model without lock-in. Jan is another open-source desktop app with a clean chat interface and local-first design. Msty offers a polished GUI with multi-model support and built-in RAG. koboldcpp is another option with a web UI and extensive configuration options.

Red Hat’s ramalama is worth a look too, a container-native model runner that explicitly credits its upstream dependencies front and center. Exactly what Ollama should have done from the start.

[anbabubabiluya]

有大佬能推荐一个部署平台吗？我也觉得 ollama 太慢了，显卡是 5060ti 16g ，最好能直接在 Windows 跑

[tool2dx]

@anbabubabiluya ollama 不慢的, 我显卡比你还差, 只有 12G 显存, 但是电脑是双显卡, 加起来就有 24G 显存. 运行 ollama 上的 qwen3.6 35b-q4 版本, 如果优化后没爆显存, 速度满速飞起. 默认是爆显存 8%, 速度降为 1/6, 超慢.

[catazshadow]

@anbabubabiluya lm studio 似乎可以

[ebushicao]

我前段时间从 ollama 换到 lm studio 了，真的好很多，相比之下 ollama 真的是个一般的玩具

[r6cb]

@anbabubabiluya #1 试试看 wsl 安装 vllm

[woctordho]

@anbabubabiluya 用 llama.cpp 就行了

[metalvest]

对普通用户来说这些都可以忽略，好用就行，看看豆包为什么用户这么多就知道了

[rammiah]

lm-studio 支持服务器运行吗？ ollama 主要是拉模型方便，modelscope ，hf 都能用

[01802]

最近不用 ollama ，为了方便，koboldcpp 都行

[catazshadow]

@rammiah 服务器用 llama-swap 调 llama.cpp 就行了

[julyclyde]

@rammiah 我总感觉 ollama 和 docker 有点像

[my3157]

ollama ggml models 要切回 llama-server 了 https://github.com/ollama/ollama/pull/15122

[jackqian]

苹果用 omlx 是不是好点？

[seakingii]

@rammiah 支持的.LM STUDIO 更方便.