TE
TechEcho
Home24h TopNewestBestAskShowJobs
GitHubTwitter
Home

TechEcho

A tech news platform built with Next.js, providing global tech news and discussions.

GitHubTwitter

Home

HomeNewestBestAskShowJobs

Resources

HackerNews APIOriginal HackerNewsNext.js

© 2025 TechEcho. All rights reserved.

LM Studio – Discover, download, and run local LLMs

461 pointsby victormustarover 1 year ago

33 comments

reustleover 1 year ago
This looks great!<p>If you&#x27;re looking to do the same with open source code, you could likely run Ollama and a UI.<p><a href="https:&#x2F;&#x2F;github.com&#x2F;jmorganca&#x2F;ollama">https:&#x2F;&#x2F;github.com&#x2F;jmorganca&#x2F;ollama</a> + <a href="https:&#x2F;&#x2F;github.com&#x2F;ollama-webui&#x2F;ollama-webui">https:&#x2F;&#x2F;github.com&#x2F;ollama-webui&#x2F;ollama-webui</a>
评论 #38385697 未加载
评论 #38382156 未加载
评论 #38384068 未加载
评论 #38383975 未加载
评论 #38384237 未加载
omneityover 1 year ago
I really like LM Studio and had it open when I came across this post. LM Studio is an interesting mixture of:<p>- A local model runtime<p>- A model catalog<p>- A UI to chat with the models easily<p>- An openAI compatible API<p>And it has several plugins such as for RAG (using ChromaDB) and others.<p>Personally I think the positioning is very interesting. They&#x27;re well positioned to take advantage of new capabilities in the OS ecosystem.<p>It&#x27;s still unfortunate that it is not itself open-source.
评论 #38382028 未加载
评论 #38379692 未加载
pentagramaover 1 year ago
Curious about this and I just download it.<p>Want to try uncensored models.<p>I have a question, looking for the most popular &quot;uncensored&quot; model I just find &quot;TheBloke&#x2F;Luna-AI-Llama2-Uncensored-GGML&quot;, but it has 14 files to download between 2 to 7 GB, I just download the first one: <a href="https:&#x2F;&#x2F;imgur.com&#x2F;a&#x2F;DE2byOB" rel="nofollow noreferrer">https:&#x2F;&#x2F;imgur.com&#x2F;a&#x2F;DE2byOB</a><p>I try the model and it works: <a href="https:&#x2F;&#x2F;imgur.com&#x2F;a&#x2F;2vtPcui" rel="nofollow noreferrer">https:&#x2F;&#x2F;imgur.com&#x2F;a&#x2F;2vtPcui</a><p>I should download all the 14 files to get better results?<p>Also, asking how to make a bomb it looks that at least this model isn&#x27;t &quot;uncesored&quot;: <a href="https:&#x2F;&#x2F;imgur.com&#x2F;a&#x2F;iYz7VYQ" rel="nofollow noreferrer">https:&#x2F;&#x2F;imgur.com&#x2F;a&#x2F;iYz7VYQ</a>
评论 #38378915 未加载
评论 #38381963 未加载
评论 #38379271 未加载
评论 #38383559 未加载
eurekinover 1 year ago
This app could use some simple UI improvements:<p>- The chatbox field has a normal &quot;write here&quot; state, when no chat is really selected. I thought my keyboard broke until I discovered that<p>- I didn&#x27;t find a way to set cuda acceleration before loading a model, only managed to set gpu offloaded layers and using &quot;relaunch to apply&quot;<p>- Some HugginFace models are simply not listed and there&#x27;s no indication about why. I guess models are really curated, but somehow presented as a HuggingFace browser?<p>- Scrolling in the accordion parts of the interface seems to be responding to mouse wheel scroll only. I have a mouse with a damaged one and couldn&#x27;t find a way to reliably navigate to bottom drawers<p>That said, I really liked the server tab, which allowed for initial debugging very easily
评论 #38377924 未加载
评论 #38377936 未加载
andy99over 1 year ago
I don&#x27;t mean this as a criticism, I&#x27;m just curious because I work in this space too: who is this for? What is the niche of people savvy enough to use this who can&#x27;t run one of the many open source local llm software? It looks in the screenshot like it&#x27;s exposing much of the complexity of configuration anyway. Is the value in the interface and management of conversation and models? It would be nice to see info or even speculation about the potential market segments of LLM users.
评论 #38378019 未加载
评论 #38383671 未加载
评论 #38378173 未加载
评论 #38378058 未加载
评论 #38429681 未加载
评论 #38390548 未加载
porcodaover 1 year ago
Amusing qualifications for the senior engineering roles they’re hiring for:<p>“Deep understanding of what is a computer, what is computer software, and how the two relate.”<p>Right after the senior ML role that requires people understand how to write “algorithms and programs.”<p>Kinda hard to take those kinds of requirements seriously.
评论 #38383848 未加载
评论 #38383766 未加载
kgeistover 1 year ago
For my experiments with new self-hostable models on Linux, I&#x27;ve been using a script to download GGUF-models from TheBloke on HuggingFace (currently, TheBloke&#x27;s repository has 657 models in the GGUF format) which I feed to a simple program I wrote which invokes llama.cpp compiled with GPU support. The GGUF format and TheBloke are a blessing, because I&#x27;m able to check out new models basically on the day of their release (TheBloke is very fast) and without an issue. However, the only frontend I have is console. Judging by their site, their setup is exactly the same as mine (which I implemented over a weekend), except that they also added a React-based UI on top. I wonder, how they&#x27;re planning to commercialize it, because it&#x27;s pretty trivial to replicate, and there&#x27;re already open-source UI&#x27;s like oogabooga.
评论 #38378189 未加载
评论 #38380464 未加载
评论 #38380926 未加载
hnuser123456over 1 year ago
This works, but I&#x27;ve noticed that my CPU use goes up to about 30 percent, all in kernel time (windows), after installing and opening this, even when it&#x27;s not doing anything, on two separate machines... I also hear the fan spinning fast on my laptop.<p>Killed the LM studio process and re-opened it and the ghost background usage is down to about 5%.
machiawelicznyover 1 year ago
<a href="https:&#x2F;&#x2F;github.com&#x2F;enricoros&#x2F;big-agi">https:&#x2F;&#x2F;github.com&#x2F;enricoros&#x2F;big-agi</a> seems better and is open source
pointlessoneover 1 year ago
M1 is only 3 years old and no one cares to support intel macs any more. There are surely a lot of them out there. Are they that much worse to run LLMs on?
评论 #38377869 未加载
whartungover 1 year ago
I’m late to the game about this. So I’ll ask a stupid question.<p>As a contrived example, what happens if you feed the LoTR books, the Hobbit, the Silmarillion, and whatever else is germane, into an LLM?<p>Is there a base, empty, “ignorant” LLM that is used as a seed?<p>Do you end up with a Middle Earth savant?<p>Just how does all this work?
评论 #38385552 未加载
评论 #38386961 未加载
rgbrgbover 1 year ago
LMStudio is great, if a bit daunting. If you’re on Mac and want a native open source interface, try out FreeChat <a href="https:&#x2F;&#x2F;www.freechat.run" rel="nofollow noreferrer">https:&#x2F;&#x2F;www.freechat.run</a>
评论 #38380750 未加载
RecycledEleover 1 year ago
This is what I use on Windows 10.<p>I have an HP z440 with an E5-1630 v4 and 64GB DDR4 quad channel RAM.<p>I run LLMs on my CPU, and the 7 billion parameter models spit out text faster than I can read it.<p>I wish it supported LMMs (multi modal models.)
isilofiover 1 year ago
Disappointing, no proper Linux support. Just &quot;ask on discord&quot;.
评论 #38386546 未加载
评论 #38384861 未加载
MuffinFlavoredover 1 year ago
1. Mistral<p>2. Llama 2<p>3. Code Llama<p>4. Orca Mini<p>5. Vicuna<p>What can I do with any of these models that won&#x27;t result in 50% hallucinations&#x2F;it recommending code with APIs that don&#x27;t exist&#x2F;it recommending basically regurgitated StackOverflow historical out of date answers (that it was trained on) for libraries that have had their versions&#x2F;APIs change, etc?<p>Can somebody share one real use case they are using any of these models for?
评论 #38413982 未加载
评论 #38386142 未加载
cyphertechincover 1 year ago
If you just want to try something quick. You can try AskCyph LITE <a href="https:&#x2F;&#x2F;askcyph.cypherchat.app" rel="nofollow noreferrer">https:&#x2F;&#x2F;askcyph.cypherchat.app</a>. It runs AI model natively on browser without having to do any installation, etc.
manyosoover 1 year ago
For those looking for an open source alternative with Mac, Windows, Linux support check out GPT4All.io
评论 #38380352 未加载
smusamashahover 1 year ago
Why purple or some shade of purple is the color of all AI products? For some reason, the landing pages of AI products immediately remind of Crypto products. This one does not have Crypto vibes but the colour is purple. I don&#x27;t get why.
评论 #38379904 未加载
评论 #38378149 未加载
cztomsikover 1 year ago
Also, if you don&#x27;t know what all the toggles are for, this is a simpler attempt by me: <a href="https:&#x2F;&#x2F;www.avapls.com&#x2F;" rel="nofollow noreferrer">https:&#x2F;&#x2F;www.avapls.com&#x2F;</a>
hugovieover 1 year ago
LMStudio is great to run local LLMs, also support OpenAI-compatible API. In the case you need more advance UI&#x2F;UX, you can use LMStudio with MindMac(<a href="https:&#x2F;&#x2F;mindmac.app" rel="nofollow noreferrer">https:&#x2F;&#x2F;mindmac.app</a>), just check this video for details <a href="https:&#x2F;&#x2F;www.youtube.com&#x2F;watch?v=3KcVp5QQ1Ak" rel="nofollow noreferrer">https:&#x2F;&#x2F;www.youtube.com&#x2F;watch?v=3KcVp5QQ1Ak</a>.
评论 #38388257 未加载
评论 #38378760 未加载
评论 #38381408 未加载
deskamessover 1 year ago
Newbie question... Is this purely for hosting <i>text</i> language models? Is there something similar for image models? i.e., upload an image and have some local model provide some detection&#x2F;feedback on it.
LoganDarkover 1 year ago
I was working on something like this by myself, but ADHD deleted all my motivation. I&#x27;ll definitely want to try this soon, especially if it&#x27;s free!<p>I hope it supports my (3060) GPU, though.
stuckinhellover 1 year ago
After the latest Chatgpt debacles, the poor performance I&#x27;m getting from 4 turbo, I&#x27;d really like a local version of chatgpt4 or equivalent. I&#x27;d even buy a new pc if I had too.
评论 #38382970 未加载
FooBarWidgetover 1 year ago
The settings say saving chats can take 2 GB. Why? What states do chat LLMs have? Isn&#x27;t the only state the chat history text?
sumedhover 1 year ago
How does this App make money?
评论 #38377585 未加载
cvhashim04over 1 year ago
Wow this is sleek, good job.
DrNosferatuover 1 year ago
The Linux version is not loading models. What’s your experience?
jhoechtlover 1 year ago
Is this an alternative to privategpt or GPT4All?
评论 #38390761 未加载
repleteover 1 year ago
RIP Intel users
d_meezeover 1 year ago
So if you suspect I am using this for business related purposes you may take any action you want to spy on me? Such Terms. Very Use.
评论 #38377747 未加载
评论 #38377568 未加载
评论 #38378378 未加载
评论 #38380908 未加载
评论 #38378121 未加载
sunsmileover 1 year ago
Considering the code is closed source and they can change the ToS anytime to send conversation data to their servers whenever they want, i would like to know what would be the benefit of using this over ChatGPT?
评论 #38382658 未加载
chatmastaover 1 year ago
Am I missing something here? I&#x27;m on a recent M2 machine. Every model I&#x27;ve downloaded fails to load immediately when trying to load it. Is there some way to get feedback on the reason for failure, like a log file or something?<p>EDIT: The problem is I&#x27;m on macOS 13.2 (Ventura). According to a message in Discord, the minimum version for some (most?) models is 13.6.
评论 #38380943 未加载
cloudkingover 1 year ago
Is anyone using open source models to actually get work done or solving problems in their software architecture? So far I haven&#x27;t found anything near the quality of GPT-4.
评论 #38380699 未加载
评论 #38384887 未加载
评论 #38382348 未加载
评论 #38380970 未加载
评论 #38380934 未加载