7 results for “vision-language model”
Liquid AI released an experimental DSpark draft model for its LFM2.5-VL-3B vision-language model, delivering up to 3.13× faster decoding on Apple silicon. It ships with day-one llama.cpp, MLX-VLM, and SGLang support.
DeepSeek open-sourced its experimental V4-Flash-Vision-Exp multimodal model on Hugging Face under MIT license on August 31, 2026. The release gives developers local access to the 305B-parameter vision-language model that previously ran only on DeepSeek's API platform.
The PyTorch Foundation is adding an Introduction Track and a full-day PyTorch Associate Training on October 19, 2026 in San Jose. Completing the training earns a $250 voucher for the PyTorch Certified Associate exam.
A developer known as slvDev has demonstrated a 28.9-million-parameter language model generating text at 9.88 tokens per second on an ESP32-S3. Running a language model on a sub-$10 microcontroller changes the cost floor for local AI.
Google DeepMind announced its Gemma open models have surpassed one billion downloads and 100,000 community variants. The milestone underscores Gemma's role as a default substrate for open-weights AI development across space, healthcare, and research.
Liquid AI has released the LFM2.5 model family, a comprehensive suite of open-weight models designed to run entirely on edge devices without cloud. The LFM2.5 releases address three critical constraints that have limited on-device AI.
NVIDIA has introduced two new Jetson Thor modules aimed at bringing more capable AI workloads to robots and edge devices. The Jetson T3000 and T2000 are designed for systems that need to process vision, language and sensor data locally.