Unsloth AI

Run and train models locally with the Unsloth Desktop app. 🦥

[Unsloth AI @UnslothAI]

Introducing Unsloth Desktop 🦥
The first desktop app to run and train models locally.

• Open-source. Runs on Mac, Windows and Linux
• Supports MLX, diffusion image/video, audio, GGUF
• Connect Claude Code and Codex to local LLMs
• 50% more accurate, self-healing tool calls + sandboxed code exec
• Works for CPU + multiGPU setups - NVIDIA, AMD, Intel, Mac
• Train models 2× faster with 70% less VRAM
• Private web search, deep research, RAG, MCP and exports (NVFP4, GGUF)
• Use Unsloth’s OpenAI-compatible API and cloud models
• Securely deploy LLMs remotely and access anywhere

Unsloth Desktop is now available on https://t.co/xxBDOI9ApK and GitHub.

GitHub: https://t.co/2kXqhhvLsb
Blog and Guide: https://t.co/CYosNAQHva

[Unsloth AI @UnslothAI]

@Alibaba_Qwen We're so ready! We can't wait to upload GGUFs for people to run Qwen4 locally. Let's go! 💜🦥

[Unsloth AI @UnslothAI]

Qwen3.8-Flash-Next GGUFs now run faster with less thinking and less token use.

Unsloth Dynamic V3.1 GGUFs bring thinking & token use to match 95% of full precision Qwen3.8-Flash.

Results: 50% fewer tokens + 15% higher accuracy vs same size quants.

GGUF: https://t.co/vXkjO3W0fj

[Unsloth AI @UnslothAI]

We’re releasing new Qwen3.8-Flash-Next GGUFs with 15% higher accuracy.

Unsloth Dynamic V3.1 outperforms others by >15% on Terminal Bench, DeepSWE & more benchmarks (256K context).

Run on 32GB+ RAM setups.

GGUF: https://t.co/vXkjO3W0fj
Blog: https://t.co/LLMclyJTeL

[Unsloth AI @UnslothAI]

We’re releasing new Qwen3.8-Flash-Next GGUFs with 15% higher accuracy.

Unsloth Dynamic V3.1 outperforms others by >15% on Terminal Bench, DeepSWE & more benchmarks (256K context).

Run on 32GB+ RAM setups.

GGUF: https://t.co/vXkjO3W0fj
Blog: https://t.co/LLMclyJTeL

[Unsloth AI @UnslothAI]

We benchmarked DeepSeek-V4.1-Flash-1017 GGUFs on Terminal Bench, DeepSWE & more on 512K context. Unsloth ranks highest overall.

1-bit Unsloth GGUF scores 68.1 on DeepSWE, 72.2 on Terminal-Bench, 52.7 on AutomationBench. >10% ahead of other quants.

GGUF: https://t.co/1kD14VTAYP

[Unsloth AI @UnslothAI]

We’re releasing new DeepSeek-V4.1-Flash-1017 GGUFs, ranking highest across benchmarks.

Dynamic V3.1 leads across nearly all benchmarks: GPQA Diamond, AIME25, LiveCodeBench v6, MMLU-Pro, Aider & more.

Run on 64GB+ RAM.

GGUF: https://t.co/1kD14VTAYP
Blog: https://t.co/YPEmDLas7d

[Unsloth AI @UnslothAI]

@MiniMax_AI Thank you MiniMax team! Thank you for supporting the open-source community and releasing amazing open models. 🥰

[Unsloth AI @UnslothAI]

@coldniko Can't wait for you all to run DeepSeek-V4.1-Flash Unsloth GGUFs more efficiently in Strata! 🥰

[Niko Veit @coldniko]

Unsloths support for Deepseek is here! 👀

+ Improvements on Strix
+ Improvements on parallel requests
+ Improvements on DGX Spark
+ Improvements on Intel B-series

See more at: https://t.co/bptoXmkAJa

[Unsloth AI @UnslothAI]

We’re releasing new DeepSeek-V4.1-Flash-1017 GGUFs, ranking highest across benchmarks.

Dynamic V3.1 leads across nearly all benchmarks: GPQA Diamond, AIME25, LiveCodeBench v6, MMLU-Pro, Aider & more.

Run on 64GB+ RAM.

GGUF: https://t.co/1kD14VTAYP
Blog: https://t.co/YPEmDLas7d

[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

[Unsloth AI @UnslothAI]

@MistralAI @cognition Congrats Mistral on the release of Le Chonk! We made some GGUFs for folks who can run it locally 🐱 https://t.co/O3X5q9O8Q7

[Unsloth AI @UnslothAI]

Mistral Le Chonk can now run locally!

The 1 trillion parameter model runs on a Mac Studio with our 1-bit GGUF which retains 91% top-1 accuracy.

Le Chonk is the strongest Western open model to date.

GGUF: https://t.co/irNXvfVGNg
Guide: https://t.co/StUa0S2XP6

[Unsloth AI @UnslothAI]

Mistral Le Chonk can now run locally!

The 1 trillion parameter model runs on a Mac Studio with our 1-bit GGUF which retains 91% top-1 accuracy.

Le Chonk is the strongest Western open model to date.

GGUF: https://t.co/irNXvfVGNg
Guide: https://t.co/StUa0S2XP6

[Mistral AI @MistralAI]

Today, we release the weights of a new and improved Le Chonk, advancing the open frontier for agentic coding and cybersecurity.

💻 Built to build: Le Chonk ranks #1 on @cognition’s FrontierCode among open models, and sets a new benchmark for Pareto efficiency on @artificialanalysis.

🛡 Built to defend: State-of-the-art in cyberdefense, put through the paces by the world's leading cyber vendors, including @CrowdStrike, @cloudflare, @rubrik, @zscaler, and others.

Built for sovereignty: Make it yours. Download the weights on @huggingface , customize it with Mistral Forge, and deploy it wherever you need it.

Read more from our team and customers 👇:

[Unsloth AI @UnslothAI]

Your local LLM can now take control of a browser and complete tasks autonomously via Unsloth!

Qwen3.8-27B successfully controlled the browser to complete tasks like chess, painting, with no human intervention.

GitHub: https://t.co/aZWYAtakBP
Guide: https://t.co/bhq8pHfAL2

[MiniMax (official) @MiniMax_AI]

MiniMax M3.1 Flash meets the @UnslothAI community. 🐙🦥✨

Unsloth’s Dynamic GGUFs bring our 428B MoE model to a 143.9GB 2-bit footprint, with 91.5% top-1 token agreement in their evaluation across seven domains.

That means a lower memory barrier to self-hosting, deployment through Unsloth Desktop and llama.cpp, and an OpenAI-compatible API for existing apps and agents.

With 78K+ GitHub stars and over 500M model downloads on Hugging Face, Unsloth gives M3.1 Flash a path into an established community of developers running, evaluating and building with open models.

Open weights. Local control. More ways to build.

[Unsloth AI @UnslothAI]

@NVIDIARTXSpark @danielhanchen @NaderLikeLadder Looking forward to seeing what people create with NVIDIA RTX Spark, especially with local training and RL 🦥💚

[Unsloth AI @UnslothAI]

@MiniMax_AI We're super excited to be supporting MiniMax-M3.1-Flash! Can't wait to see what people build with it. 🥰🙏

[NVIDIA RTX Spark @NVIDIARTXSpark]

Getting started with @UnslothAI on RTX Spark? Just run the .exe.

@danielhanchen and @NaderLikeLadder got hands-on with NVIDIA RTX Spark to talk about running and training AI models locally, exploring reinforcement learning, and making it easier to start building with Unsloth.

[Unsloth AI @UnslothAI]

MiniMax-M3.1-Flash can now run locally!

We made 2-bit GGUF retain 91.5% top 1 accuracy while being 45% smaller. Run on 150GB RAM.

MiniMax-M3.1-Flash is the strongest open model for its size & among the best overall.

GGUF: https://t.co/A8Xp9uqpq1
Guide: https://t.co/gW5gp25niu

[MiniMax (official) @MiniMax_AI]

MiniMax M3.1 Flash: Space Performance + Bunny Speed

🚀🐰 Yes, Space Bunny - which has topped global leaderboards with 200T+ tokens - was an earlier version of M3.1 Flash.

💰Redefining the performance economics of agentic AI. M3.1 Flash achieves frontier-level intelligence across key tasks such as Cowork (Automation-Bench: 62%; ALE: 30%), Coding (DeepSWE: 74%) and Visual Reasoning (BabyVision: 91%), at 1/3 the cost of M3 and 3x the speed.

API pricing (flat rate): $0.15 / $0.60 per 1M input/output tokens, with cache reads at $0.015 / 1M tokens.

Model weights will arrive on Oct 23.

API: https://t.co/fHRdSV73Hr
M Plan: https://t.co/XfJWSyauda
MiniMax Code for desktop: https://t.co/SGmLTI2HQm

[Unsloth AI @UnslothAI]

@Kimi_Moonshot Congrats Kimi team on another open K3.1 Pro model! Despite its massive 3T parameter size, we'll see what we can do to make GGUF quants for folks who want to run it locally. 🙏

[Unsloth AI @UnslothAI]

NVIDIA releases Nemotron-3.5-Bolt-E4B, a new model that runs locally on 6GB RAM. 💚

Bolt-E4B can run on edge devices like phones and delivers top-tier performance for its size. Trained on Gemma 4, it supports vision.

GGUF: https://t.co/NsDphrHOGC
Guide: https://t.co/RIgVixplpT

[NVIDIA AI @NVIDIAAI]

Available now: NVIDIA Nemotron 3.5 Bolt E4B 4GB ⚡️

Our newest small open model is built for local assistants, interactive characters and robots that can carry on a conversation and use tools to get things done.

Watch Reachy Mini chat and move, with Bolt handling conversation and NVIDIA Cosmos handling vision. Both models run locally on Jetson Orin Nano 8GB.

Learn more: https://t.co/B8ODaWMn0O

[Unsloth AI @UnslothAI]

@MiniMax_AI Thank you MiniMax team for more open models! We will try to make some M3.1 Flash quants for people who can run the model locally! 🥰

[Unsloth AI @UnslothAI]

@reflection_ai @opencode Thanks for sharing, this is a super cool demo of automated fine-tuning! 🔥