Image, Video and Audio

stable-diffusion-3.5-medium-amdnpu-medusa: File List

Stability AI releases Stable Diffusion 3.5 Medium optimized for AMD NPUs in ONNX format, improving prompt adherence a ...

Engines and Tools

llama.cpp v0.8.0: Multimodal Enhancements and LFM3 Support

llama.cpp v0.8.0 introduces LiquidAI LFM3 support, real-time audio streaming APIs, and significant memory management ...

Engines and Tools

Unsloth 0.1.912-beta: Multi-LoRA Batching and Faster Startup

Unsloth 0.1.912-beta introduces Multi-LoRA batching for efficient training, faster startup, and improved support for ...

Engines and Tools

ggml v0.28.0 Released: Sparse Attention and MoE Optimizations

The latest ggml release introduces GGML_OP_TOP_K_MASK for sparse attention, MoE optimizations for CUDA, and expanded ...

Engines and Tools

Jan v0.8.8 Released: llama.cpp Upgrade and Security Enhancements

Jan v0.8.8 updates the internal llama.cpp engine to 0.7.0, introduces MoE settings, and implements critical security ...

Image, Video and Audio

LongLive2.0-Robot-L Robot Video Generation Model: File List

Efficient-Large-Model has released the weights for LongLive 2.0 Robot-L, an autoregressive image-to-video model desig ...

New Models

Qwen3.8-27B-NVFP4-DGX-SPARK-V2 NVFP4 Quantized 27B Model: 24GB+ VRAM

Explore the unofficial release of Qwen3.8-27B NVFP4 combined with a 64k MTP recipe for accelerated speculative decodi ...

Engines and Tools

Ollama v0.40.12 Released: Adds Liquid AI LFM3 and d1 Models

Ollama v0.40.12 is out, adding support for Liquid AI LFM3 and d1 decision models, plus Apple Silicon prompt processin ...

Engines and Tools

Magnitude @magnitudedev/cli@0.2.12 Released

Release notes for magnitudedev/magnitude @magnitudedev/cli@0.2.12 covering installer improvements, model ID changes, ...

New Models

d1-2B-GGUF Text, Image, and Video Decision-Making Model: 4GB+ VRAM

LiquidAI has released the GGUF version of d1-2B, a multimodal decision model built on LFM3-VL-2B designed for text, i ...