Bionic is the agent for your computer https://xitter.gq/t.co/YS5uiRQ7TI
New York, USA
Joined May 2023
- Tweets2.8K
- Following83
- Followers67.2K
- Likes8.9K
You can now use oMLX in LM Studio!
Download the new engine and use it with MLX models you already have.
Excited to work with with @jundotkim and @huggingface to make this happen! πΎπ§π
oMLX is a performant and popular MLX engine for Apple Silicon, created and led by @jundotkim.
It is open-source, with an active and enthusiastic community. Check it out! github.com/jundot/omlx
LFM3 is live in LM Studio!
Fits in about 1 GB of memory.
Model page: lmstudio.ai/models/lfm3
Introducing π»π΅πΌπΉ: our new generation of Liquid Foundation Models. With a new tri-hybrid architecture and new multimodal encoders, the LFM3 family is the ideal model suite for specialized intelligence.
> 6 model instances, across text, audio, vision, and omni modalities, generative and decision models.
> π»π΅πΌπΉ-π·.π½π±: text, 256k context window.
> π»π΅πΌπΉ-π
π»-πΈπ±: vision-language model with video-input support for spatial understanding
> π»π΅πΌπΉ-π°ππππ-πΈπ±: tool calls, voice chat, reasoning in 18 languages.
> π»π΅πΌπΉ-πΎπππ-πΈπ±: an omni model combines vision, audio, and language.
> ππ·-πΈπ± and ππ·-πΎπππ-πΈπ±: decision models with typed outputs and calibrated probabilities in a single pass. Omni adds audio input.
> fine-tune on 1 GPU.
> a new tri-hybrid architecture
> architecture optimized for 14 processor classes across GPUs, CPUs, and NPUs.
> π»π΅πΌπΉ-π
π»-πΈπ± is a beast. It performs competitively with Gemma 4 12B (6x larger), and Gemini 3.5 Flash Lite, and GPT-5.6 Luna, with 1.9B parameters.
> π»π΅πΌπΉ-π·.π½π± is #1 on the Pareto frontier of device intelligence πππππππ.ππππππ.ππ
Every modality for specialized intelligence. Pick the one that fits your use case, customize it, and run it on-device.
1/ π§΅
Introducing: Read Aloud π
Powered by a tiny local TTS model, the excellent Phonon by @GradiumAI.
We're excited to bring you Flint by @Recursive_SI in LM Studio on day 0!
β’ 40B MoE, 2.5B active
β’ 262K token context window
β’ Apache 2.0
β’ Trained for local agentic coding model
Requires about 24GB to run locally on your machine, performs impressively on benchmarks.
Introducing Flint, @Recursive_SIβs first model: a fast local coding model built with our automated research system, the Eureka Machine.
β’ Best-in-class fast local coding
β’ Up to 2x faster than comparable models: 125+ tokens/sec on a MacBook Pro, 150+ on RTX Spark
β’ 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.
DeepSeek-V4.1-Flash-1017 is now live in LM Studio Bionic!
1M context β’ image input β’ highly cost effective
US-hosted with full ZDR.
Try it out for coding tasks!
π DeepSeek-V4.1-Flash-1017 is here!
Stronger benchmark performance, faster task completion, and shorter outputs than the previous versionβa Pareto improvement in performance and cost. Now live on our website, app, and API.
π οΈ 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
Beam (501B MoE) by Reflection is now live in Bionic!
US-hosted and ZDR.
Letβs go! ππΎ
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: huggingface.co/reflection
Nemotron 3.5 Super VL from @NVIDIAAI is live in LM Studio!
β’ 120B total / 12B active MoE
β’ Supports vision input, reasoning
β’ Trained for visual understanding, tool use
Requires ~70GB RAM to run locally π πΎ
lmstudio.ai/models/nemotron-β¦
LM Studio retweeted
State β local decision model β action
Check out @liquidai's d1 decision model playing Lmmy Run, all on its own π¦πΎ
Served 100% on-device, making decisions in a fraction of a second
LM Studio retweeted
LM Studio 0.4.26 is out now!
β’ β‘οΈ `/v1/systemone` and `/v1/decisions` APIs
β’ πΎ Coexistence with Bionic
β’ π¨ UI updates and bug fixes
Yes, you can now point your Bionic agent to models loaded in your LM Studio.
lmstudio.ai/docs/developer/jβ¦
Also new in Bionic 1.1.8:
- /v1/systemone and /v1/decisions API support
- Run Bionic at the same as LM Studio
lmstudio.ai/changelog/bionicβ¦