LM Studio

Bionic is the agent for your computer

[LM Studio @lmstudio]

Introducing: Read Aloud 🔊

Powered by a tiny local TTS model, the excellent Phonon by @GradiumAI.

[yags @yagilb]

Incredible things are happening at LM Studio headquarters

[LM Studio @lmstudio]

Read Aloud is available for Mac in Bionic 1.1.9, supporting 1 multilingual voice.

Bionic for Windows and Linux will gain TTS in the next version.

[LM Studio @lmstudio]

Introducing: Read Aloud 🔊

Powered by a tiny local TTS model, the excellent Phonon by @GradiumAI.

[LM Studio @lmstudio]

@realTOMWANG123 @Recursive_SI GGUF only at the moment. Grab it from staff picks. MLX on the way

[LM Studio @lmstudio]

We're excited to bring you Flint by @Recursive_SI in LM Studio on day 0!

• 40B MoE, 2.5B active
• 262K token context window
• Apache 2.0
• Trained for local agentic coding model

Requires about 24GB to run locally on your machine, performs impressively on benchmarks.

[Richard Socher @RichardSocher]

Introducing Flint, @Recursive_SI’s first model: a fast local coding model built with our automated research system, the Eureka Machine.

• Best-in-class fast local coding
• Up to 2x faster than comparable models: 125+ tokens/sec on a MacBook Pro, 150+ on RTX Spark
• Built from scratch in under 4 months

Private, unmetered intelligence on your own machine. Open weights available now on @huggingface, run it locally on your favorite framework or try it for free on @opencode or @pidotdev.

[LM Studio @lmstudio]

We’ve added new US-based capacity for DeepSeek-V4.1-Flash-1017 in Bionic.

Should run into much fewer rate limits now. Working to add more!

[LM Studio @lmstudio]

@vampaz @Recursive_SI Please download the model from the staff picks within the app. GGUF support is in place, MLX on the way

[LM Studio @lmstudio]

https://t.co/YTzNxgC4GP

[LM Studio @lmstudio]

@squidlord Working to add capacity 🛠️, sorry about that. We feel the pain!

[LM Studio @lmstudio]

@techtunes67 Local operation is completely free. Only cloud models are billed

[LM Studio @lmstudio]

DeepSeek-V4.1-Flash-1017 is now live in LM Studio Bionic!

1M context • image input • highly cost effective

US-hosted with full ZDR.

Try it out for coding tasks!

[DeepSeek @deepseek_ai]

🚀 DeepSeek-V4.1-Flash-1017 is here!

Stronger benchmark performance, faster task completion, and shorter outputs than the previous version—a Pareto improvement in performance and cost. Now live on our website, app, and API.

🛠️ Optimized for @DeepSeekHarness, Tencent CodeBuddy, WorkBuddy, and more. Upgrade to DeepSeek Harness v0.2.1-rc.1 or later for the best experience with the new model.

1/4

[LM Studio @lmstudio]

@JJJ40526907 Working to increase capacity!

[LM Studio @lmstudio]

@stanislav_3fun Do you mind sharing what broke? We’d love a description of the bug so we can fix it

[LM Studio @lmstudio]

Bionic can now show live updating previews of your docs, sheets, and slides!

[LM Studio @lmstudio]

https://t.co/949BiWCjSN

[LM Studio @lmstudio]

Beam (501B MoE) by Reflection is now live in Bionic!

US-hosted and ZDR.

Let’s go! 🚀👾

[Reflection @reflection_ai]

Beam is now available across platforms, with open weights under the Apache 2.0 license - in collaboration with an ecosystem of 40+ partners.

We're releasing:
- Weights, tokenizer, and reference implementation
- BF16, FP8 and NVFP4 weights and a DFlash2 drafter
- The open source harness we built and trained Beam on: Mirror CLI

Weights and model card on Hugging Face: https://t.co/tPqWpk9RXL

[LM Studio @lmstudio]

@reflection_ai Let's go! 🚀

[LM Studio @lmstudio]

Nemotron 3.5 Super VL from @NVIDIAAI is live in LM Studio!

• 120B total / 12B active MoE
• Supports vision input, reasoning
• Trained for visual understanding, tool use

Requires ~70GB RAM to run locally 🚀 👾

https://t.co/rp5lsOWWP6

[LM Studio Developers @lmstudiodevs]

State → local decision model → action

Check out @liquidai's d1 decision model playing Lmmy Run, all on its own 🦖👾

Served 100% on-device, making decisions in a fraction of a second

[LM Studio @lmstudio]

@mikedoise Cool! Which model are you planning to use for the implementation work?