Morgan Funtowicz

Machine Learning Engineer - @HuggingFace / Paris 🇫🇷

[Morgan Funtowicz @MorganFunto]

@jeffboudier @Microsoft You can grab LlamaApp from the Microsoft Store directly https://t.co/jBm8kLxCRO

[Llama moved to @llama_app @llama_cpp]

Our picks from this week's model releases 🦙
→ LFM3 by Liquid AI: small models for text, image and speech, with d1 decision models
→ Mistral Large 4: large, 1M context frontier
→ Flint by Recursive: mid-sized, built for coding agents

Get them at https://t.co/GP9txkNJEd

[Morgan Funtowicz @MorganFunto]

Llama for @Windows v0.14 is out 😎
- Handle llama:// deeplink
- Improved local GGUF import
- Various bug fixes

Available now https://t.co/QNqwmZVP5C

[Morgan Funtowicz @MorganFunto]

Your local AI just got more Windows-native 🦙

Llama for Windows v0.13.0 is out!

🖼️ Share images & text to Llama
⚡ Speculative decoding support
💻 See which models likely fit your hardware
🔗 llama:// deep links
Give it a spin 👇
https://t.co/LuKdne4fkf

[Morgan Funtowicz @MorganFunto]

Hey @Windows users, local AI is for you too🥳
Llama for Windows v0.12.0 is out!

🖥️ llama.cpp in your Windows 11 tray
🤗 Download models in one click
😎 Improved UX flow

👉 https://t.co/wyb5PA9lq2

[Morgan Funtowicz @MorganFunto]

https://t.co/ZACm32lfRL

[Morgan Funtowicz @MorganFunto]

Local AI has never been easier for Windows users.
Open source. Truly local. Zero cloud.
Llama for Windows runs llama.cpp models entirely on your hardware — download & manage models, chat from anywhere with Alt+Space
Your prompts never leave your machine
🦙https://t.co/D0zOjzZWzP

[Morgan Funtowicz @MorganFunto]

What's next? Let us know what you'd like to see supported!

✍️ https://t.co/57p9v9woQn

[Morgan Funtowicz @MorganFunto]

Serving @OpenAI Whisper, powered by @vllm_project, deployed on @huggingface Inference Endpoint, with astonishing @Gradio demo ... What else? 😎

AI community is all you need to create blazing fast whisper transcriptions 💥🚀

More in our blog 📰 https://t.co/zE1G4VAvHb

[Morgan Funtowicz @MorganFunto]

Reference implementation sources 🧐https://t.co/tQgANybDa9

[Morgan Funtowicz @MorganFunto]

Qwen3 235B is now available on HuggingChat! And you know what? It's blazing fast✌️

👉https://t.co/NSBBjNue1Z

[Morgan Funtowicz @MorganFunto]

Last but not least, vLLM and llama.cpp are currently being worked on! 🚀

Initial artifacts for testing will be made available for the community around end of Q1'25 🛠️ and follow up blog posts will pop as we start rolling them out.

[Morgan Funtowicz @MorganFunto]

Anyone looking to deploy LLMs in production,🤗got something for you👀

@huggingface TGI is expanding its capabilities to bring support for different inference backends (vLLM, TensorRT-LLM, llama.cpp, etc. etc.) 🏋️

🗞️ More info in our last blogpost https://t.co/0vQnSXQZaJ

[Morgan Funtowicz @MorganFunto]

TensorRT-LLM, from our partner @nvidia, is the first backend we will be shipping. We are currently wrapping up the last parts.

It'll bring cutting edge float8, quantization & sparsity support🤏

We'll soon publish a part 2 with more in-depth about this integration, stay tuned!

[Morgan Funtowicz @MorganFunto]

@BramVanroy @AMDInstinct @Azure Stay tuned 🤠

[Morgan Funtowicz @MorganFunto]

Want to leverage @AMDInstinct MI300x GPUs for LLMs? Check out how easy it is and the performance in our blog post! 🚀

👉https://t.co/dyDXrQ6HYU

Still hungry?🧐Register for the next HuggingCast on June 6th 🎙️https://t.co/zUYJp41QRW

PS: Deploy these GPUs on @Azure right now! 😱

[Morgan Funtowicz @MorganFunto]

Hello @Free_1337 👋🏻, plus de fibre depuis le 19/12 sur Lessard le National (71530) est-ce que vous avez de la visibilité sur une résolution future ? 🤗🙏🏻