Unsloth AI (@UnslothAI) / X

Unsloth AI

697 posts

Unsloth AI

@UnslothAI

Train and run models locally! 🦥 github.com/unslothai/unsl…

San Francisco, CA

Joined November 2023

Pinned
Unsloth AI
@UnslothAI
Mar 17
Introducing Unsloth Studio ✨ A new open-source web UI to train and run LLMs. • Run models locally on Mac, Windows, Linux • Train 500+ models 2x faster with 70% less VRAM • Supports GGUF, vision, audio, embedding models • Auto-create datasets from PDF, CSV, DOCX •
00:00
Unsloth AI
@UnslothAI
Jul 17
Gemma 4 is now faster and much more accurate! 🚀 Google made huge improvements to tool-calling and chat accuracy, reliability + speed. To get fixes, re-download our updated GGUF, MLX, NVFP4 quants! Unsloth quants: huggingface.co/collections/un… Gemma 4 Guide: unsloth.ai/docs/models/ge…
Google Gemma
@googlegemma
Jul 15
We’re rolling out some big improvements to Gemma 4, fueled by incredible community feedback and contributions! Here is a breakdown of what’s being fixed and updated in this release: 🧵👇
Unsloth AI reposted
Maziyar PANAHI
@MaziyarPanahi
Jul 16
I played Thinking Machines' new Inkling a 2-minute doctor's visit, on my Mac Studio 🔥 The patient came in about her knee. Inkling listened to the whole thing and flagged the heart failure instead. It heard the real audio, not a transcript. 975B params, the 1-bit GGUF
00:00
Unsloth AI
@UnslothAI
Jul 15
You can now run Thinking Machines Inkling! Inkling is a 975B open model with image, audio and 1M context support. We quantized Inkling to Dynamic 1-bit (-86% size) and retained 74.2% of top-1% accuracy. Run on 280GB. Guide: unsloth.ai/docs/models/in… GGUF: huggingface.co/unsloth/inklin…
Thinking Machines
@thinkymachines
Jul 15
Today, we are introducing Inkling. Inkling reasons efficiently across text, image, and audio modalities. We are making the full weights available. thinkingmachines.ai/news/introduci… Available today for fine-tuning on Tinker. Play with it in the Inkling Playground. 🧵
Unsloth AI
@UnslothAI
Jul 14
We’re releasing Gemma 4 NVFP4 quants that run 1.5× faster on your GPU. Gemma-4-12B NVFP4 works on 11GB VRAM. 26B-A4B hits 13K tok/s (B200). Unsloth NVFP4 enables faster, more accurate 4-bit Blackwell inference. Blog: unsloth.ai/docs/basics/nv… Gemma NVFP4: huggingface.co/collections/un…
Unsloth AI
@UnslothAI
Jul 13
We collaborated with AWS on a complete guide to LLM Quantization and Deployment. Learn about: • Model formats, dynamic quants & making your own • GGUF, NVFP4 or FP8 • Right tools & deploy on Amazon SageMaker • Benchmark quality, latency & cost Read: aws.amazon.com/blogs/machine-…
Unsloth AI
@UnslothAI
Jul 10
We’re releasing new Qwen3.6 quants that run 2.5× faster on your GPU. Qwen3.6-27B NVFP4 runs on 24GB VRAM. 35B-A3B can hit 17,561 tok/s (B200). We also improved accuracy, tool calling, agent use, and looping. Guide: unsloth.ai/docs/models/qw… Qwen3.6 NVFP4: huggingface.co/collections/un…
Unsloth AI
@UnslothAI
Jul 7
DeepSeek-V4 can now run locally with Unsloth GGUFs! 🐳 Run lossless DeepSeek-V4-Flash on 168GB RAM. 3-bit works on 110GB Mac, RAM, VRAM setups. We improved the chat template. Run via Unsloth Studio or llama.cpp. Guide: unsloth.ai/docs/models/de… GGUF: huggingface.co/unsloth/DeepSe…
Unsloth AI
@UnslothAI
Jun 25
What’s your go-to local model right now?
Unsloth AI
@UnslothAI
Jun 23
1-bit GLM-5.2 GGUF vs. Claude 4.8 Opus vs. GPT-5.5 We gave 3 models the same prompt and compared one-shot outputs. The 1-bit GLM-5.2 GGUF ran locally on a Mac Studio M3 Ultra with 256GB RAM at ~21.6 tok/s. Which output do you like best? GGUF: huggingface.co/unsloth/GLM-5.…
00:00
Unsloth AI
@UnslothAI
Jun 18
GLM-5.2 can now be run locally!🔥 The 2-bit model retains ~82% accuracy after we shrunk it from 1.51TB to 238GB (-84% size). Run on a 256GB Mac or RAM/VRAM setups. GLM-5.2 is the strongest open model to date. Guide: unsloth.ai/docs/models/gl… GGUF: huggingface.co/unsloth/GLM-5.…
Unsloth AI
@UnslothAI
Jun 18
GLM-5.2 can now be run locally!🔥 The 2-bit model retains ~82% accuracy after we shrunk it from 1.51TB to 238GB (-84% size). Run on a 256GB Mac or RAM/VRAM setups. GLM-5.2 is the strongest open model to date. Guide: unsloth.ai/docs/models/gl… GGUF: huggingface.co/unsloth/GLM-5.…
Z.ai
@Zai_org
Jun 16
Introducing GLM-5.2: Frontier Intelligence, Open Weights - Significant improvements in coding and agentic tasks - Strong long-horizon capabilities with a 1M context window - Two levels of reasoning effort: GLM-5.2 (max) pushes the limits, while GLM-5.2 (high) strikes a strong
Unsloth AI
@UnslothAI
Jun 18
You can run GLM-5.2 and other models directly in Unsloth Studio:
GitHub - unslothai/unsloth: Unsloth Studio is a web UI for training and running open models like...
From github.com
Unsloth AI
@UnslothAI
Jun 15
You can now run Kimi K2.7 Code locally! 🌘 We shrank the 1T model to 325GB (-48%) via Dynamic 2-bit where important layers are upcasted. Run at >40 tok/s on 330GB RAM/VRAM setups. Run full precision on 610 GB. Guide: unsloth.ai/docs/models/ki… GGUF: huggingface.co/unsloth/Kimi-K…
Kimi.ai
@Kimi_Moonshot
Jun 12
🌘 Kimi-K2.7-Code, our latest coding model, is now released and open-sourced! 🔷 Improved coding & agent performance over K2.6: +21.8% on Kimi Code Bench v2, +11.0% on Program Bench, and +31.5% on MLS Bench Lite. 🔷 Reasoning efficiency: Less overthinking, with 30% lower
Unsloth AI reposted
Ivan Fioravanti ᯅ
@ivanfioravanti
Jun 12
Local AI in action! MiniMax M3 unning locally on a single M3 Ultra 512GB in Unsloth Studio! 🔥 Here UD-Q5_K_XL decoding at 32.5 toks/s!
00:00
Unsloth AI
@UnslothAI
Jun 12
MiniMax M3 can now be run locally!🔥 MiniMax-M3 is a new 428B (23B active) open model with 1M context that performs on par with Gemini 3.1 Pro. Run Dynamic 2-bit GGUF on 138GB RAM/VRAM or 3-bit on 165GB. GGUF: huggingface.co/unsloth/MiniMa… Guide: unsloth.ai/docs/models/mi…
MiniMax (official)
@MiniMax_AI
Jun 12
MiniMax M3, Open-Weight, Now On Hugging Face , with only ~428B parameters and ~23B activated parameters Weights: huggingface.co/MiniMaxAI/Mini… MiniMax Sparse Attention: huggingface.co/papers/2606.13…