TechniqueAgents3 recent entries10 Apr 2026llama.cpp now supports various small OCR models that can run on low-end devices. These models are small enough to run on GPU with 4GB VRAM, …llama.cpp now supports various small OCR models that can run on low-end devices. These models are small enough to run on GPU with 4GB VRAM, and some of them can even run on CPU with decent performance→4 Jun 2026Highlighting recent advances in multi-GPU and tensor parallel support in llama.cpp Over the last few months llama.cpp maintainers and engine…Highlighting recent advances in multi-GPU and tensor parallel support in llama.cpp Over the last few months llama.cpp maintainers and engineers from NVIDIA collaborated to improve the multi-GPU perfor
TechniqueFine-tuning1 recent entries10 Aug 2026Meta released Muse Glimmer 30B: multimodal model for your Claw/Pi setups 🔥 we tested and fine-tuned the model for you, and shipped day-0 su…Meta released Muse Glimmer 30B: multimodal model for your Claw/Pi setups 🔥 we tested and fine-tuned the model for you, and shipped day-0 support in transformers and llama.cpp, including DFlash for 2-4
TechniqueMultimodal2 recent entries10 Apr 2026llama.cpp now supports various small OCR models that can run on low-end devices. These models are small enough to run on GPU with 4GB VRAM, …llama.cpp now supports various small OCR models that can run on low-end devices. These models are small enough to run on GPU with 4GB VRAM, and some of them can even run on CPU with decent performance→10 Aug 2026Meta released Muse Glimmer 30B: multimodal model for your Claw/Pi setups 🔥 we tested and fine-tuned the model for you, and shipped day-0 su…Meta released Muse Glimmer 30B: multimodal model for your Claw/Pi setups 🔥 we tested and fine-tuned the model for you, and shipped day-0 support in transformers and llama.cpp, including DFlash for 2-4