Ultimately, the onus at every VC backed local LLM startup is to launch a cloud based offering, because that's the only potential path in sight for venture scale returns.
Yup, it's the main reason I don't use LM studio more. I only use it to try out new models/quants, then use llama.cpp directly to host them. LM Studio also doesn't do stuff like audio input and often has bugs that pure llama.cpp doesn't so it can be a net negative for certain use cases.
I am aware of it, and I dabble with Unsloth Studio and use the llama-server approach.
I would obviously prefer an open source, open weights stack.
But I guess a paradox is that as long as there are open source options I could use, a solid agentic environment that I can use with my own open weights is something I might pay for, in a similar sort of way to paying for a Mac when I could use only Linux.
If someone wanted to make their entire income from, say, making the BBEdit of LLM harnesses, that would be a viable strategy. Sooner or later people need to make an income somewhere. My own feeling is that Apple should acquire LM Studio, but if they said "this is $X per year" I might consider it, given the attention to detail.
This kind of thing just makes me think Apple will get to a point where they have good enough local models and good enough harnesses for doing things, and most normal people will just use them… Does the LLM become another interface to computing?
i believe that for most people on the street, for most tasks, a Chat GPT 3.5 era LLM is sufficient enough. sprinkle in tool calling and other things, and that becomes enough. if you can prioritize that level of a model on-device (baking it in etc), then you can bifurcate AI users between those unwilling to pay and those who are willing to pay A LOT for frontier model performance.
I have thought this for a while. Computing 1.0 meant that we needed to learn the computer’s language to interact with the computer fully. Computing 2.0 is that now the computer has learned our language instead.
I’m not sure what interacting with the computer fully means, but I don’t think it’s true about most computer users. They use software which invariably speaks to the user through visual metaphors and conceptual abstractions. Nothing has changed in that regard. This is true even of most programmers using high level languages.
Nothing has changed at the level of computation either, hardware speaks the same vocabulary and of electrical signals as ever.
This question hinges on whether model advancement plateaus enough for machine sized models to compare to frontier performance. If it does, the answer is yes. If it doesn’t, the answer is no
Neural machines were always going to be an alternative computing paradigm to von Neumann machines. Had it not been for Minsky we would arguably have gotten to a point where they're useful sooner. But why do you say that as if it's a small thing?
Why wait? People are already doing their work on OpenAI and Anthropic's servers, Apple Intelligence servers could quickly subsume any "local" model work that you want to do.
That way everyone has access, even with older devices, and it's a subscription! Then Apple can tie their APIs into the ecosystem you love at a flat cost you can afford. No need to support local model integration in the first place, problem solved.
based on their apple intelligence demos they are optimizing their products for their core demo of 55-95 year old boomers who talk out loud to think and read every page of the nytimes. you are miles away from the US consumer product experience here.
Apple’s System Model is actually pretty good but is hard-limited to a 4K context length. This is OK for small Python utilities that need a model for applications that operate on small amounts of data, but is a disappointing limitation.
That said, and this is off topic: Siri on the newest iOS beta is surprisingly good now. I asked it what model it was using yesterday and it said Gemini for difficult problems, then secure Apple model in cloud, and local Apple model.
Why would I use this over any other harness? I suppose they're wrapping it all up in a nice package for enterprise, especially ones that want to control their LLM usage for cost and data security compared to the cloud frontier models.
Hey everyone! Yagil the founder of LM Studio here. If you want to take Bionic for a spin with GLM 5.2 / Kimi K2.6 / Kimi Coder K2.7, email your lmstudio.ai username to hn-jul16@lmstudio.ai and I'll load your account with some credits!
Try it out for coding (in a "Code" project) and document creation / manipulation (in a "Work" project). In Work projects we have automatic checkpointing for every change the agent makes. Would love to hear your feedback.
I have never previously tried a agentic harness for local models yet, but I really love LM Studio so I gave Bionic a shot immediately after reading this!
First impression: it works great. I use Codex as my main agent, and the UI looks similar enough that it's familiar and simple to get started. I just pointed it to my existing LM Studio models library, ran Qwen3.6 35B, and the results are exactly what I would hope for.
I did notice some rough edges that might be worth improving, however:
- Current working directory is not the clearest on the main page of the app. It shows the project name, but is missing the prominent working directory label like Codex has.
- The model seems to load when you hit Enter, but it shows "Working" instead of of "Loading model".
- There doesn't seem to be a way to pre load the model, it seems like you have to send it something to load the model.
- I don't see a way to easily unload the model like the eject button in LM Studio without quitting the app
- I pointed it to a directory called "GitHub & Projects" and it somehow ended up making a new folder called "GitHub & Projects". Yes, I know the name is weird but it shouldn't have done that.
trusting them to not retain your data and never train on it is for fools. this is something they say to gain adoption and that they will reverse with an obscure 'privacy policy update' down the road.
Great to see LM Studio expanding into agent workflows. Local model tooling keeps getting better, and having an open-source option for this is valuable for developers who want to keep their data private.
What the hell, as far as i see this is not open source but has the tag line "Meet LM Studio Bionic, the AI agent made for open models" How can someone justify this complete clash of values, who is even an audience for something this. cursed, the agent and harness layer being open is probably more important than your models as you can just switch models every week and they are commodity.
47 comments
[ 4.0 ms ] story [ 55.5 ms ] threadSince most people are unaware of this fact.
I don't think we need closed-source developer tools, especially ones where they might restrict access if they decide to start charging for them later.
I would obviously prefer an open source, open weights stack.
But I guess a paradox is that as long as there are open source options I could use, a solid agentic environment that I can use with my own open weights is something I might pay for, in a similar sort of way to paying for a Mac when I could use only Linux.
If someone wanted to make their entire income from, say, making the BBEdit of LLM harnesses, that would be a viable strategy. Sooner or later people need to make an income somewhere. My own feeling is that Apple should acquire LM Studio, but if they said "this is $X per year" I might consider it, given the attention to detail.
i believe that for most people on the street, for most tasks, a Chat GPT 3.5 era LLM is sufficient enough. sprinkle in tool calling and other things, and that becomes enough. if you can prioritize that level of a model on-device (baking it in etc), then you can bifurcate AI users between those unwilling to pay and those who are willing to pay A LOT for frontier model performance.
Nothing has changed at the level of computation either, hardware speaks the same vocabulary and of electrical signals as ever.
Could you describe the change you are observing?
That way everyone has access, even with older devices, and it's a subscription! Then Apple can tie their APIs into the ecosystem you love at a flat cost you can afford. No need to support local model integration in the first place, problem solved.
It already is.
That said, and this is off topic: Siri on the newest iOS beta is surprisingly good now. I asked it what model it was using yesterday and it said Gemini for difficult problems, then secure Apple model in cloud, and local Apple model.
> use the largest frontier open source models through LM Studio Secure Cloud
Try it out for coding (in a "Code" project) and document creation / manipulation (in a "Work" project). In Work projects we have automatic checkpointing for every change the agent makes. Would love to hear your feedback.
First impression: it works great. I use Codex as my main agent, and the UI looks similar enough that it's familiar and simple to get started. I just pointed it to my existing LM Studio models library, ran Qwen3.6 35B, and the results are exactly what I would hope for.
I did notice some rough edges that might be worth improving, however:
- Current working directory is not the clearest on the main page of the app. It shows the project name, but is missing the prominent working directory label like Codex has. - The model seems to load when you hit Enter, but it shows "Working" instead of of "Loading model". - There doesn't seem to be a way to pre load the model, it seems like you have to send it something to load the model. - I don't see a way to easily unload the model like the eject button in LM Studio without quitting the app - I pointed it to a directory called "GitHub & Projects" and it somehow ended up making a new folder called "GitHub & Projects". Yes, I know the name is weird but it shouldn't have done that.
* locked to a single dir, so no system wide access.
* no local web search, can be fixed ddg or local mcp.
* no ssh, I want to have it ssh into my server and do the work.
* doesnt show the model being loaded, needs a bar/% counter.
* Can you drag/drop documents in the work dirs, or only + add them?
I love lm-studio, so cant wait to see how this goes. For local I normally use opencode + lmstudio.