‌Hugging Face (Twitter)

RT @linoy_tsaban: still getting over the fact HunyuanImage 3.0 is here (less than a month since HunyuanIamge 2.1) and then I see it's 80B params 🤯
+ Image editing is coming 👀
FUN TIMES
https://huggingface.co/tencent/HunyuanImage-3.0

Hugging Face (Twitter)

RT @multimodalart: the 𝑳𝒐𝑹𝑨 𝔣𝔯𝔢𝔷𝔫𝔦 is LIVE

Train Qwen, Wan and FLUX LoRAs for free for 1 week (Sep 29 - Oct 6th)

We cobbled together @ostrisai AI Toolkit & the new @huggingface Jobs API together

Hugging Face (Twitter)

RT @Saboo_Shubham_: oLLM is a lightweight Python library for local large-context LLM inference.

Run gpt-oss-20B, Qwen3-next-80B, Llama-3.1-8B on ~$200 consumer GPU with just 8GB VRAM. And this is without any quantization - only fp16/bf16 precision.

100% Opensource.

Hugging Face (Twitter)

RT @_akhaliq: HunyuanImage 3.0 is out on Hugging Face

A Powerful Native Multimodal Model for Image Generation

80B parameters, Largest Image Generation MoE Model

Reasons with world knowledge

Generates text within images

vibe coded a text to image app with anycoder using @fal

Hugging Face (Twitter)

RT @reach_vb: Introducing Hugging Face Inference Provider Starter App 💥

Built w/ @nextjs and @OpenAIDevs SDK - powered by SoTA open-weights LLMs 🤗

Create seamless experiences without worrying about boilerplate via streaming and structured outputs

Check out the app in comments below 👇

Hugging Face (Twitter)

RT @dylan_ebert_: I made a vibe coding game engine

the problem: people are trying to vibe code games. it kind of works at first, but as the project grows, things begin to fall apart

why? and what can we do about it? ⤵️

step 1.

Hugging Face (Twitter)

RT @NousResearch: Starting today, Psyche will train 6 new models in parallel in pursuit of creating world class open source AI.

These runs serve as the starting point for future experiments and a more thorough and empirical training process.

Hugging Face (Twitter)

RT @osanseviero: Welcome to TimesFM 2.5, a pre-trained model for times-series forecasting, which performs great in zero-shot out-of-the-box

- 200M params (down from 500M)
- 16k context (up from 2k)
- Available on Hugging Face
- Apache 2.0

Happy Monday!

Hugging Face (Twitter)

RT @ting_: DeepSeek-V3.2-Exp is live on @huggingface API, supported by @novita_labs 🤗

⚡ More efficient long-context reasoning

📊 Matches V3.1 performance, even surpasses on tasks like AIME 2025 & Codeforces

📂 Content window 163K

✅ Structured Output, Function Calling, Reasoning

Try👇

Hugging Face (Twitter)

RT @AntLingAGI: 🚀 Ring-1T-preview: Deep Thinking, No Waiting
The first 1 trillion open-source thinking model
-> Early results in natural language: AIME25/92.6, HMMT25/84.5, ARC-AGI-1/50.8, LCB/78.3, CF/94.7
-> Solved IMO25 Q3 in one shot, with partial solutions for Q1/Q2/Q4/Q5

Still evolving!

Hugging Face (Twitter)

RT @BetterStackHQ: Transformers.js lets you run AI models offline in the browser with ONNX + WebGPU. Build a chatbot with Llama 3.2, optimize performance, and try local AI tasks like object detection & background removal.

Hugging Face (Twitter)

RT @ClementDelangue: Remi plugged @openai GPT-4o to Reachy Mini and it's pretty cool. Check the mirror challenge & chess playing in particular!

Fun new capabilities:
- Image analysis: Reachy Mini can now look at a photo it just took and describe or reason about it
- Face tracking: keeps eye contact and makes interactions feel much more natural
- Motion fusion: [head wobble while speaking] + [face tracking] + [emotions or dances] can now run simultaneously
- Face recognition: runs locally
- Autonomous behaviors when idle: when nothing happens for a while, the model can decide to trigger context-based behaviors

Questions for the community:

• Earlier versions used flute sounds when playing emotions. This one speaks instead (for example the "olala" at the start is an emotion + voice). It completely changes how I perceive the robot (pet? human? kind alien?). Should we keep a toggle to switch between voice and flute sounds?

• How do the response delays...

Перейти на оригинальный пост

‌Hugging Face (Twitter)

RT @AdinaYakup: Ring-1T-preview 🔥 1T thinking model released by @AntLingAGI

https://huggingface.co/inclusionAI/Ring-1T-preview

✨ MoE architecture + 20T tokens + RLVR via ASystem
✨ Strong natural language reasoning (AIME’25: 92.6, close to GPT-5)
✨IMO tests: advanced problem-solving & reasoning

Hugging Face (Twitter)

RT @nishimiya: access any model on @huggingface directly with AI SDK

Hugging Face (Twitter)

RT @reach_vb: LETS FUCKING GOOO! - Use state of the art open LLMs with the simplicity of AI SDK 🤯

Kudos to the team on shipping this! 🤗 https://twitter.com/nishimiya/status/1973032330479669462#m

Hugging Face (Twitter)

RT @julien_c: Excited about this!

Hugging Face (Twitter)

RT @ting_: 🤗 GLM-4.6 is on @huggingface API! it's supported by @novita_labs

👇Tested it with my old prompt, building a pixel art pilot game, result is impressive!

FYI what's good about the model:

> 200K context window
> Top-tier reasoning & tool use (91.6 on BFCL v2!)
> Killer coding skills
> More agentic & great for agent products
> Human-like tone, perfect for role-play!