A plain-English guide to picking a local model for coding, writing, and AI agents - no PhD required
Last updated: June 2026
TL;DR: Jump to the bottom of the page if you want to skip the reading and go straight to my interactive AI model finder tool.
You don't need a data center or a monthly subscription to run a genuinely capable AI on your own machine anymore. A normal gaming PC can now run…
_Note
I'm going to use this post as a living document of the tools, technologies, and hardware I am currently using for the year, both personally and professionally. The idea is that it will be periodically updated throughout the year with comments as things change.
_
Even though I have a Mac Studio M2 Ultra and a desktop PC with a 7900 XTX and 5900XT, I still use my MacBook…
スマホで動くAIが1GB未満に。Googleが、軽量AIモデル「Gemma 4」に量子化を前提にした訓練（モデルを軽量化する前提で学習させる手法）を施した新しいチェックポイントを公開しました。Android Authorityが伝えています。最小構成のGemma 4 E2Bは、モ...
smhn.infoにアクセスすると、全文を読むことができます。
AI makes personal software easier to create, but it still needs a place to live. I see WordPress as an unexpected but practical platform for personal apps and data.
Since this is a medical question, you might get a good answer if you ask on the Hugging Science Discord. Generally speaking:
Here is the plainest, most honest answer.
For the way you tested it, MedGemma 1.5 4B is probably not useful enough.
If this is a Gemma 4 family device, it could be explained by the fact that Gemma 4 was released only recently and software support isn’t yet fully established; however, if that’s not the case, the issue is a different matter.
In any case, the simplest solution is to update the software (if that doesn’t resolve the issue, you’ll need to look for another solution or wait):
For the **Gemma…
WordPress as a personal tool: for keeping memories, staying in touch, owning your data. No audience required.
Mit dem Release von Gemma 4 wollte ich erst kürzlich noch einmal über Locally AI schreiben. Diese One-Man-Show für On-Device-AI stellte wieder umgehend, nur wenige Stunden nach der Veröffentlichung, Googles neuestes Open-Source-LLM als Download in seiner übersichtlichen Software bereit. In dieser Woche bekam ich einen noch triftigeren Grund für eine abermalige Erwähnung: We are excitedweiterlesen
ローカルAIの王者、スマホへ踏み出す。PCでローカルAIを動かす定番ツール「LM Studio」が、iPhoneにも本格展開しようとしています。LM Studioの開発元であるElement Labsが、iPhone/iPad/Mac向けローカルAIチャットアプリ「Locally...
smhn.infoにアクセスすると、全文を読むことができます。
If you access the HF server too frequently within a short period of time, you’re likely to encounter a 429 error right away.
To avoid this, when using LM Studio, it seems best to specify the exact location of the target model repository (e.g. lmstudio-community/Qwen3-Coder-Next-GGUF) rather than using vague model family names.
This is usually resolved by treating it as a…
If you access the HF server too frequently within a short period of time, you’re likely to encounter a 429 error right away.
To avoid this, when using LM Studio, it seems best to specify the exact location of the target model repository (e.g. lmstudio-community/Qwen3-Coder-Next-GGUF) rather than using vague model family names.
This is usually resolved by treating it as a…
If you access the HF server too frequently within a short period of time, you’re likely to encounter a 429 error right away.
To avoid this, when using LM Studio, it seems best to specify the exact location of the target model repository (e.g. lmstudio-community/Qwen3-Coder-Next-GGUF) rather than using vague model family names.
This is usually resolved by treating it as a…
_Posted by Matthew Warner, Google Product Manager_
_
_
Every developer's AI workflow and needs are unique, and it's important to be able to choose how AI helps your development. In January, we introduced the ability to choose any local or remote AI model to power AI functionality in Android Studio, and today, we're announcing the availability of Gemma 4 for AI coding assistance in Android…
The actual questions would probably look something like this:
The actual questions would probably look something like this:
The actual questions would probably look something like this:
Oh, I see. LM Studio support feature was added just recently… In cases like this, it usually takes a while to stabilize…
Yes. Roll back to a known-good baseline first. Then re-introduce LM Studio as a single isolated change. That is the lowest-risk path here. Open-LLM-VTuber’s own docs warn that the project is still unstable and not easy to install, and the official quick start still…
Oh, I see. LM Studio support feature was added just recently… In cases like this, it usually takes a while to stabilize…
Yes. Roll back to a known-good baseline first. Then re-introduce LM Studio as a single isolated change. That is the lowest-risk path here. Open-LLM-VTuber’s own docs warn that the project is still unstable and not easy to install, and the official quick start still…
Oh, I see. LM Studio support feature was added just recently… In cases like this, it usually takes a while to stabilize…
Yes. Roll back to a known-good baseline first. Then re-introduce LM Studio as a single isolated change. That is the lowest-risk path here. Open-LLM-VTuber’s own docs warn that the project is still unstable and not easy to install, and the official quick start still…
Oh, I see. LM Studio support feature was added just recently… In cases like this, it usually takes a while to stabilize…
Yes. Roll back to a known-good baseline first. Then re-introduce LM Studio as a single isolated change. That is the lowest-risk path here. Open-LLM-VTuber’s own docs warn that the project is still unstable and not easy to install, and the official quick start still…
Oh, I see. LM Studio support feature was added just recently… In cases like this, it usually takes a while to stabilize…
Yes. Roll back to a known-good baseline first. Then re-introduce LM Studio as a single isolated change. That is the lowest-risk path here. Open-LLM-VTuber’s own docs warn that the project is still unstable and not easy to install, and the official quick start still…
When trying to build a web app _with no-code_ , the real challenge—by far—is figuring out the right combination of backends, frameworks, etc. rather than the performance of the model weights provided by GGUF…
As coding models, GPT-OSS and the Qwen Coder family have long been popular. Recently, GLM has also been receiving rave reviews. Kimi (an extremely large model) is impressive too, but you’ll…
When trying to build a web app _with no-code_ , the real challenge—by far—is figuring out the right combination of backends, frameworks, etc. rather than the performance of the model weights provided by GGUF…
As coding models, GPT-OSS and the Qwen Coder family have long been popular. Recently, GLM has also been receiving rave reviews. Kimi (an extremely large model) is impressive too, but you’ll…
When trying to build a web app _with no-code_ , the real challenge—by far—is figuring out the right combination of backends, frameworks, etc. rather than the performance of the model weights provided by GGUF…
As coding models, GPT-OSS and the Qwen Coder family have long been popular. Recently, GLM has also been receiving rave reviews. Kimi (an extremely large model) is impressive too, but you’ll…
When trying to build a web app _with no-code_ , the real challenge—by far—is figuring out the right combination of backends, frameworks, etc. rather than the performance of the model weights provided by GGUF…
As coding models, GPT-OSS and the Qwen Coder family have long been popular. Recently, GLM has also been receiving rave reviews. Kimi (an extremely large model) is impressive too, but you’ll…
When trying to build a web app _with no-code_ , the real challenge—by far—is figuring out the right combination of backends, frameworks, etc. rather than the performance of the model weights provided by GGUF…
As coding models, GPT-OSS and the Qwen Coder family have long been popular. Recently, GLM has also been receiving rave reviews. Kimi (an extremely large model) is impressive too, but you’ll…
When trying to build a web app _with no-code_ , the real challenge—by far—is figuring out the right combination of backends, frameworks, etc. rather than the performance of the model weights provided by GGUF…
As coding models, GPT-OSS and the Qwen Coder family have long been popular. Recently, GLM has also been receiving rave reviews. Kimi (an extremely large model) is impressive too, but you’ll…
When trying to build a web app _with no-code_ , the real challenge—by far—is figuring out the right combination of backends, frameworks, etc. rather than the performance of the model weights provided by GGUF…
As coding models, GPT-OSS and the Qwen Coder family have long been popular. Recently, GLM has also been receiving rave reviews. Kimi (an extremely large model) is impressive too, but you’ll…
When trying to build a web app _with no-code_ , the real challenge—by far—is figuring out the right combination of backends, frameworks, etc. rather than the performance of the model weights provided by GGUF…
As coding models, GPT-OSS and the Qwen Coder family have long been popular. Recently, GLM has also been receiving rave reviews. Kimi (an extremely large model) is impressive too, but you’ll…
自宅のGPUマシンがどこでも使えるAIサーバーに？VPNサービスのTailscaleとローカルLLM実行アプリのLM Studioが連携し、新機能「LM Link」を発表しました。Tailscaleの公式ブログが2月25日に伝えています。LM Linkを使えば、自宅や職場の高性能...
[smhn.infoにアクセスすると、全文を読むことができます。
](https://smhn.info/202603-lm-link-remote-llm)