Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
3
3
Pedro Ferreira
PRO
pedromcf
Follow
0 followers
Β·
39 following
AI & ML interests
None yet
Recent Activity
liked
a Space
28 days ago
black-forest-labs/FLUX.1-dev
reacted
to
yeonseok-zeticai
's
post
with π
about 1 month ago
π Real-Time On-Device AI Agent with Polaris-4B β Run It Yourself, No Cloud, No Cost We just deployed a real-time on-device AI agent using the Polaris-4B-Preview model β one of the top-performing <6B open LLMs on Hugging Face. π± Whatβs remarkable? This model runs entirely on a mobile device, without cloud, and without any manual optimization. It was built using ZETIC.MLange, and the best part? β‘οΈ Itβs totally automated, free to use, and anyone can do it. You donβt need to write deployment code, tweak backends, or touch device-specific SDKs. Just upload your model β and ZETIC.MLange handles the rest. π§ About the Model - Model: Polaris-4B-Preview - Size: ~4B parameters - Ranking: Top 3 on Hugging Face LLM Leaderboard (<6B) - Tokenizer: Token-incremental inference supported - Modifications: None β stock weights, just optimized for mobile βοΈ What ZETIC.MLange Does ZETIC.MLange is a fully automated deployment framework for On-Device AI, built for AI engineers who want to focus on models β not infrastructure. Hereβs what it does in minutes: - π Analyzes model structure - βοΈ Converts to mobile-optimized format (e.g., GGUF, ONNX) - π¦ Generates a runnable runtime environment with pre/post-processing - π± Targets real mobile hardware (CPU, GPU, NPU β including Qualcomm, MediaTek, Apple) - π― Gives you a downloadable SDK or mobile app component β ready to run And yes β this is available now, for free, at https://mlange.zetic.ai π§ͺ For AI Engineers Like You, If you want to: - Test LLMs directly on-device - Run models offline with no latency - Avoid cloud GPU costs - Deploy to mobile without writing app-side inference code Then this is your moment. You can do exactly what we did, using your own models β all in a few clicks. π― Start here β https://mlange.zetic.ai π¬ Want to try Polaris-4B on your own app?
[email protected]
, or just visit https://mlange.zetic.ai , it is opened as free! Great work @Chancy, @Zhihui , @tobiaslee !
liked
a Space
about 1 month ago
tencent/Hunyuan3D-2.1
View all activity
Organizations
models
3
Sort:Β Recently updated
pedromcf/naruto-style
Text-to-Image
β’
Updated
Jan 3, 2024
β’
pedromcf/ppo-Huggy
Reinforcement Learning
β’
Updated
Jan 12, 2023
β’
48
pedromcf/ppo-LunarLander-v2
Reinforcement Learning
β’
Updated
Jan 12, 2023
β’
3
datasets
0
None public yet