ByteDance releases Lance multimodal model; llama.cpp gets speed boost

ByteDance has released Lance, a new 3-billion parameter open-source multimodal model designed to run on consumer GPUs. This model can process both images and text, aiming to make advanced AI capabilities more accessible. Concurrently, the popular inference engine llama.cpp has received significant performance enhancements through Multi-Threaded Pipelining (MTP), which boosts local inference speeds. Additionally, a new open-source chat client called Horizon has been launched, offering cross-platform support for interacting with local models via Ollama, as well as cloud-based AI services. AI

Summary written by gemini-2.5-flash-lite from 1 source. How we write summaries →

IMPACT Advances in lightweight multimodal models and inference engine optimizations will accelerate the development and deployment of local AI applications.

RANK_REASON Cluster covers release of open-source models and software updates for local inference. [lever_c_demoted from research: ic=1 ai=1.0]

Read on dev.to — LLM tag →

• ByteDance
• Horizon
• Lance
• llama.cpp
• Ollama

• model release
• infra
• product