Increasingly, being able to be in a Flow state with LLMs will be a competitive skill
@julien_c
-
llama.cpp now fully compatible with Vision Language Models
By
–
llama.cpp is now fully compatible with VLMs HUGE kudos to @ngxson from HF and to the @ggml_org team Here are a selection of pre-quantized models, ready to be used, from:
– @GoogleDeepMind Gemma
– @MistralAI Pixtral
– @Alibaba_Qwen VL
– @huggingface SmolVLM Give them a -
Qwen Models on Hugging Face Now Backed by Xet Storage
By
–
TL;DR: Qwen models on @huggingface are now backed by Xet storage
-
Completed Hugging Face Agents Course Unit 1 with Perfect Score
By
–
Yay! Late to the party but i got 100% at Unit 1 in the @huggingface Agents course What about you?
-
Run Tiny Agents Locally with Qwen3 and MCP Client
By
–
Thanks to the community, you can now run Tiny Agents (powered by @huggingface mcp-client in huggingface.js) fully local If you have Qwen3 14B running locally (in LM Studio for instance) – or any other tool-compatible model – just run this:
-
Testing Jinja Parser on 100K Hub Model Chat Templates
By
–
The great thing about working on top of the HF Hub is that you can validate your ideas + code based on real-world usage from the AI community. Here @xenovacom who's buiding an awesome Jinja parser in JS, is testing it over the top 100,000 model Chat Templates on the Hub.
-
Slow down AI progress for European bank holidays
By
–
Hey can we slowdown AI progress by 50% so Europeans can take their state-mandated bank holidays in May?
-
Advanced AI Future Blog Post Generation
By
–
If we had access to advanced AI from the future, we would for sure use it to write our blog posts
-
Claude 4o consistency issues raised in user critique
By
–
Yes but even 4o is not 4o given the switch it for you underneath
-
Identifying Which LLM You’re Interacting With
By
–
I want to be able to pin precisely which LLM I am talking with is that too much to ask?