LM Studio 0.4

#1

Post by jiqiren » Wed, Jan 28, 2026, 6:23 PM UTC

Re: LM Studio 0.4

#2

Post by jiqiren » Wed, Jan 28, 2026, 6:23 PM UTC

This release introduces parallel requests with continuous batching for high throughput serving, all-new non-GUI deployment option, new stateful REST API, and a refreshed user interface.

Re: LM Studio 0.4

#3

Post by minimaxir » Wed, Jan 28, 2026, 7:06 PM UTC

LMStudio introducing a command line interface makes things come full circle.

Re: LM Studio 0.4

#4

Post by syntaxing » Wed, Jan 28, 2026, 7:15 PM UTC

I’m really excited for lmster and to try it out. It’s essentially what I want from ollama. Ollama has deviated so much from their original core principles. Ollama has been broken and slow to update model support. There’s this “vendor sync” I’ve been waiting (essentially update ggml) for weeks.

Re: LM Studio 0.4

#5

Post by Helithumper » Wed, Jan 28, 2026, 7:24 PM UTC

minimaxir wrote: post #3

LMStudio introducing a command line interface makes things come full circle.

For context, LMStudio has had a CLI for a while it just required the desktop app to be open already. This makes it where you can run LMStudio properly headless and not just from a terminal while the desktop app is open.

`lms chat` has existed, `lms daemon up` / "llmster" is the new command.

Re: LM Studio 0.4

#6

Post by saberience » Wed, Jan 28, 2026, 7:29 PM UTC

What’s the main use-case for this?

I get that I can run local models, but all the paid for (remote) models are superior.

So is the use-case just for people who don’t want to use big tech’s models? Is this just for privacy conscious people? Or is this just for “adult” chats, ie porn bots?

Not being cynical here, just wanting to understand the genuine reasons people are using it.

Re: LM Studio 0.4

#7

Post by observationist » Wed, Jan 28, 2026, 7:29 PM UTC

jiqiren wrote: post #2

This release introduces parallel requests with continuous batching for high throughput serving, all-new non-GUI deployment option, new stateful REST API, and a refreshed user interface.

Awesome - having the API, MCP integrations, refined CLI give you everything you might want. I have some things I'd wanted to try with ChainForge and LMStudio that are now almost trivial.

Thanks for the updates!

Re: LM Studio 0.4

#8

Post by anonym29 » Wed, Jan 28, 2026, 7:32 PM UTC

edit: disregard, new version did not respect old version's developer mode setting

Re: LM Studio 0.4

#9

Post by tiderpenger » Wed, Jan 28, 2026, 7:35 PM UTC

saberience wrote: post #6

What’s the main use-case for this? I get that I can run local models, but all the paid for (remote) models are superior. So is the use-case just for people who don’t want to use big tech’s models? Is this just for privacy conscious people? Or is this just for “adult” chats, ie porn bots? Not being cynical here, just wanting to understand the genuine reasons people are using it.

To justify investing a trillion dollars like everything else LLM-related. The local models are pretty good. Like I ran a test on R1 (the smallest version) vs Perplexity Pro and shockingly got better answers running on base spec Mac Mini M4. It's simply not true that there is a huge difference. Mostly it's hardcoded overoptimalization. In general these models aren't really becoming better.

Re: LM Studio 0.4

#10

Post by reactordev » Wed, Jan 28, 2026, 7:36 PM UTC

saberience wrote: post #6

What’s the main use-case for this? I get that I can run local models, but all the paid for (remote) models are superior. So is the use-case just for people who don’t want to use big tech’s models? Is this just for privacy conscious people? Or is this just for “adult” chats, ie porn bots? Not being cynical here, just wanting to understand the genuine reasons people are using it.

Not always. Besides, this allows one to use a post-trained model, a heretic model, an abliterated model, or their own.

I exclusively run local models. On par with Opus 4.5 for most things. gpt-oss is pretty capable. Qwen3 as well.