Qwen-Image-NVFP4 4-Bit Quantized Image Generation Model: 48GB+ VRAM
Explore nvidia/Qwen-Image-NVFP4, a 4-bit floating-point quantized text-to-image open-weight model optimized for NVIDI ...
Unsloth v0.1.906-beta Released with Browser Use and Text Diffusion
Unsloth v0.1.906-beta is released, featuring autonomous browser use, Qwen-Image-2.1-Turbo support, text-diffusion LLM ...
Weekly Open-Weight Model News: llama.cpp v0.6.0, FastH3, Beam 501B
Catch up on the latest open-weight generative model news, including major updates to llama.cpp v0.6.0, FastH3 video g ...
vllm-d3 GGUF Models Released: Decision Models for Local Run
GGUF versions of the vllm-d3 decision model series are now available from ggml-org, optimized for local execution via ...
Magnitude CLI 0.2.7 Released: Major Speedups and Fixes
Magnitude CLI 0.2.7 is released, bringing massive inference speedups, Arch Linux support, and stability fixes for App ...
StreamRender-H3 Real-Time Video Generation Model: 8GB+ VRAM, File List
Learn about StreamRender-H3, a real-time streaming diffusion rendering model by Efficient-Large-Model for interactive ...
clef-omni 30B Multimodal Decision Model: 80GB+ VRAM
Discover Cloudflare/clef-omni, a multimodal decision model based on Qwen/Qwen3-Omni-30B-A3B-Instruct designed for dir ...
Open WebUI v0.12.0 Released: Real-Time Voice & VRM Avatars
Open WebUI v0.12.0 is out, featuring real-time voice calls with OpenAI models, VRM 3D avatars, tool search, performan ...
Voxtral-Mini-4B-Realtime-Arabic Speech Recognition Model: 4GB+ VRAM
Mistral AI has released Voxtral-Mini-4B-Realtime-Arabic, a streaming speech recognition model supporting Arabic diale ...
Qwen-Image-2.1-Turbo 8-Step Fast Image Generation Model: 48GB+ VRAM
Discover Qwen-Image-2.1-Turbo, an open-weight text-to-image and image editing model offering high-quality generation ...