PaddleOCR-VL: Boosting Multilingual Document Parsing via a 0.9B Ultra-Compact Vision-Language Model Paper • 2510.14528 • Published Oct 16, 2025 • 122
view article Article Prefill and Decode for Concurrent Requests - Optimizing LLM Performance Apr 16, 2025 • 67
view post Post 3342 GPT-4.1-mini level model right in your iPhone 🤯 openbmb/MiniCPM-V-4 is only 4B while surpassing GPT-4.1-mini in vision benchmarks 🔥allows commercial use as well! See translation 🚀 5 5 + Reply
Llama 3.2 Collection Meta goes small with Llama3.2, both text only 1B and 3B, and the 11B Vision models. • 14 items • Updated about 1 month ago • 13
meta-llama/Llama-3.2-1B-Instruct Text Generation • 1B • Updated Oct 24, 2024 • 4.12M • • 1.34k