magnitudedev/magnitude v0.2.6 Released: Major Mac Speedups
magnitudedev/magnitude v0.2.6 is out, bringing massive prompt processing speedups and stability fixes for Apple Silic ...
Reflection Announces Beam: A 501B Open-Weight MoE Model
Reflection has announced Beam, its first open-weight MoE model with 501B total parameters. Explore community reaction ...
Two Quantized Versions of Audio-Visual Video Generation Model FastH
Two quantized versions of the audio-visual video generation model FastH3 V2 have been released by the FastVideo team ...
FastH3 Trim: 8-Step Text-to-Video Model with Audio Support
Explore FastH3 Trim, an 8-step text-to-video model with audio support released by the FastVideo team, available in BF ...
llama.cpp v0.6.0 Released with llama_batch_ext and Metal Boosts
llama.cpp v0.6.0 is out, featuring the new llama_batch_ext API, major Metal backend speedups, web UI updates, and new ...
ggml v0.26.0 Released with Sparse Flash Attention & New Backends
ggml v0.26.0 is released, featuring sparse Flash Attention optimizations, expanded quantization support for WebGPU, a ...
Naive-N0.5-Flash MoE Model for AI Research and Coding: ~690GB Memory
NaiveAI has released Naive-N0.5-Flash, a 309B MoE model with 15.5B active parameters, a 1M context window, and MIT li ...
vLLM v0.31.0 Released: Fast Restart and Hardware Optimization
vLLM v0.31.0 is released, featuring fast restart, DeepSeek optimizations, prefix cache security improvements, and bro ...
Local AI Model Weekly Highlights: Structured Output & Video LoRAs
Weekly roundup of local generative AI models: structured output models, video generation LoRAs, inference engines, an ...
DiarizationLM-Gemma-4-E4B-v1 Vision-Language Model: 8GB+ VRAM
Learn about DiarizationLM-Gemma-4-E4B-v1, an open-weights LLM for speech processing by Google based on Gemma 4 E4B, w ...