Run and train models locally with the Unsloth Desktop app. š¦„ https://xitter.cf/t.co/2kXqhhvdCD
San Francisco, CA
Joined November 2023
- Tweets806
- Following483
- Followers102K
- Likes15.2K
Run Flint locally on 24GB RAM via Unsloth Dynamic GGUFs!
Flint is the strongest MoE model under 50B parameters.
Recursiveās Apache-2.0 model has 39.8B parameters (2.5B active). Run at 125 t/s on Mac, 150 on RTX Spark
GGUF: huggingface.co/unsloth/flintā¦
Guide: unsloth.ai/docs/models/flint
Introducing Flint, @Recursive_SIās first model: a fast local coding model built with our automated research system, the Eureka Machine.
ā¢ Best-in-class fast local coding
ā¢ Up to 2x faster than comparable models: 125+ tokens/sec on a MacBook Pro, 150+ on RTX Spark
ā¢ 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.
Congrats Recursive team on the amazing model! š We made some Flint GGUFs so you can run it locally on 24GB RAM! huggingface.co/unsloth/flintā¦
Congrats Ornith team on another amazing open model. šŗ We made Ornith-1.5-122B GGUFs to enable you to run locally on 64GB RAM setups!
huggingface.co/unsloth/Ornitā¦
Unsloth AI retweeted
š„³ Ornith-1.5-122B Unsloth GGUFs are now available!
š§” Thanks for the awesome work by @UnslothAI
š huggingface.co/unsloth/Ornitā¦
Aloha!šŗ Meet Ornith-1.5-122B: No Tradeoff Between Strong and Fast
Stronger. Faster. Leaner. Ornith-1.5-122B delivers frontier-level capabilities with exceptional inference efficiency. With superior instruction following, stronger task decomposition, and deeper understanding of real-world workflows, it achieves state-of-the-art performance among open-source models of comparable size, while running on a single NVIDIA DGX card!!
Open weights under the MIT license.
Coding
ā
SWE-bench Verified: 0.845
ā
TB2.1: 0.813
ā
CyberGym: 0.800
ā
NL2Repo: 0.512
Agentic
ā
HLE: 0.446
ā
BrowseComp: 0.785
ā
MCP-Atlas: 0.746
ā
Toolathlon: 0.708
š¤Hugging Face: huggingface.co/ornith-ai/Ornā¦
We canāt wait to see what you build with Ornith-1.5-122B.
This is amazing thanks DeepSeek! We made DeepSeek-V4.1-Flash-1017 possible to run locally on 128GB RAM setups via Dynamic GGUFs!
DeepSeek V4.1-Flash-1017 can now run locally! š³
We made 1-bit retain ~88.2% accuracy while shrinking size from 508GB to 250GB (ā52%).
Run on a 128GB+ RAM device.
V4.1 Flash 1017 is the strongest open model to date
Guide: unsloth.ai/docs/models/deepsā¦
GGUF: huggingface.co/unsloth/DeepSā¦
DeepSeek V4.1-Flash-1017 can now run locally! š³
We made 1-bit retain ~88.2% accuracy while shrinking size from 508GB to 250GB (ā52%).
Run on a 128GB+ RAM device.
V4.1 Flash 1017 is the strongest open model to date
Guide: unsloth.ai/docs/models/deepsā¦
GGUF: huggingface.co/unsloth/DeepSā¦
š DeepSeek-V4.1-Flash-1017 is here!
Stronger benchmark performance, faster task completion, and shorter outputs than the previous versionāa Pareto improvement in performance and cost. Now live on our website, app, and API.
š ļø 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
You can now run and train 120B+ parameter models locally on a laptop! NVIDIA RTX Spark is here. š
With Unsloth and RTX Spark, train diffusion, decision, multimodal models ~2.7Ć faster with optimized kernels and binaries for CUDA on ARM. All local with up to 128GB unified memory
NVIDIA RTX Spark is here.
Build AI locally, bring your creative ideas to life, and take your favorite games along.
A new beginning for @Windows PCs starts today.
Unsloth AI retweeted
how do you fine-tune a decision model on your own data?
in these two notebooks, you'll learn:
ā¢ how to prepare the training data
ā¢ how to fine-tune our d1-3B decision model
ā¢ using @UnslothAI and @huggingface TRL
all within 30 minutes on a free-tier GPU.
unsloth: github.com/Liquid4All/cookboā¦
TRL: github.com/Liquid4All/cookboā¦
ps: how adorable are these halloween kitties? š»
Meta releases Muse Spark Open, a new SOTA open model.
Run on a Mac Studio via Dynamic 2-bit Unsloth GGUFs.
Muse-Spark-Open-816B-A42B supports text, images, video and audio input with 1M context.
GGUF: huggingface.co/unsloth/Muse-ā¦
Guide: unsloth.ai/docs/models/muse-ā¦
Muse Spark Open -- weights releasing today -- runs great on new Mac Studios thanks to work with @johnternus and Apple.
Congrats Meta and thank you for more open-weight models! š„°
For those who can run Muse Spark Open locally, we made Dynamic GGUFs: huggingface.co/unsloth/Muse-ā¦
NVIDIA releases 2 new models: Nemotron-3.5-Bolt and Nemotron-3.5-Super-VL.
Nemotron-3.5-Bolt-74B-A9B runs on 24GB RAM. It delivers top-tier performance for its size.
Super-VL-120B-A12B runs on 82GB RAM.
Bolt GGUF: huggingface.co/unsloth/NVIDIā¦
Guide: unsloth.ai/docs/models/nemotā¦
Super GGUF: huggingface.co/unsloth/NVIDIā¦
Unsloth AI retweeted
Video: Decision model trained in ~2 mins on a single DGX Spark using Unsloth! Qwen3.5-2B as base model.
Just follow instruction here: unsloth.ai/docs/basics/trainā¦
Congrats! We're excited to make Qwen-Image-2.1-Turbo quants and GGUFs for it so everyone can run it locally! š
You can now train your own Decision model with our free notebook! š”
Qwen3.5-4B will generate decisions instead of text on just 8GB VRAM locally.
Learn to data prep (state, questions, gold answers), train, serve.
Notebook: colab.research.google.com/giā¦
Guide: unsloth.ai/docs/basics/trainā¦
You can now train your own Decision model like Jev locally!
We increased Qwen3.5 0.8Bās aggregate accuracy from 20.7% to 74.3% across 3 decision benchmarks - on just 4GB VRAM.
Turn any LLM like Qwen3.8, Gemma 4 into decision models with our open-source Unsloth repo.
We fine-tuned with a Clef head using Unsloth and LoRA (r=64) for one epoch, increasing downstream accuracy from 30ā37% to 78%.
GitHub: github.com/unslothai/unsloth
Guide and Notebooks: unsloth.ai/docs/basics/trainā¦
Windows now has sandboxing!
Microsoft released an open-source repo, mxc, for sandboxed code execution.
We collaborated with Windows to add mxc OS level sandboxing to Unsloth which adds just <100 ms of overhead.
GitHub: github.com/unslothai/unsloth
Guide: unsloth.ai/docs/new/studio/sā¦
With just 2.5GB VRAM, you can train your own Decision Model using small models like Laya.
Training is simply done through a UI interface. Video tutorial and analysis are in our guide.
GitHub repo: github.com/unslothai/unsloth
You can now train your own Decision model like Jev locally!
We increased Qwen3.5 0.8Bās aggregate accuracy from 20.7% to 74.3% across 3 decision benchmarks - on just 4GB VRAM.
Turn any LLM like Qwen3.8, Gemma 4 into decision models with our open-source Unsloth repo.
We fine-tuned with a Clef head using Unsloth and LoRA (r=64) for one epoch, increasing downstream accuracy from 30ā37% to 78%.
GitHub: github.com/unslothai/unsloth
Guide and Notebooks: unsloth.ai/docs/basics/trainā¦
Google releases EmbeddingGemma 2, a new open model that runs locally on 0.5GB RAM.
The 740M parameter Apache 2.0 model combines a 270M text model with vision (170M) + audio (300M).
Run & train the model via Unsloth.
GGUF: huggingface.co/unsloth/embedā¦
Guide: unsloth.ai/docs/models/embedā¦
Open-source is so back! Go Mistral! š„³š±
We can't wait to make quants for those who can run Le Chonk locally!
Unsloth AI retweeted
We're co-hosting an open source party with @HuggingFace! š¤š¦„
Come join us, we'll be handing out @UnslothAI merch, showcasing our upcoming features and more!
It'll be a super fun night with lots of demos, DJs, food and more.
Join: luma.com/OpenTogether
Use code: NOSLOTHSHERE to get in.