Meituan's open-weight talking-avatar model now holds a consistent face for more than 10 minutes, generates in 8 steps, and placed second only to OmniHuman-2.0 in Meituan's own human-preference vote.
TurinTech's Artemis GGUF build packs Google's Gemma 4 E2B into 2.05 to 2.31 GB, and it holds up much better than other public files in that size range.
ai-coustics' Quail Voice Focus 2.3 keeps the main speaker even when they're quiet or far from the mic. It runs on CPU in about 30 ms and cuts word errors by up to 43%.
Red Hat's 4-bit NVFP4 build of Gemma 4 26B-A4B cuts memory needs by about 75%. It keeps 97 to 99% of the original model's accuracy on most benchmarks, but agentic tool use and hard math take bigger hits.
Nanonets-OCR2-3B is a compact vision-language model that turns messy documents into clean, LLM-ready markdown with semantic tags for tables, equations, signatures, and more.
AtomicChat shipped refusal-ablated GGUF builds of Liquid AI's LFM2.5-24B-A2B MoE, cutting English refusals from 96.3% to 1.2% while gaining MMLU points.
A community-trained LoRA for Krea 2 focused on Asian character generation has crossed one million downloads, pulling the open-weights base model into the spotlight.
ChatR Labs ships a rank-128 LoRA merged into Qwen-Image-2.1 across GGUF, FP8, INT8, NVFP4 and NF4 builds, with an uncensored tune that improves adult-prompt adherence while running on 4 to 14 GB of VRAM.
Alibaba's compact 8B reasoning model ships in quantized GGUF formats, offering hybrid thinking mode, 131K context, and local inference on modest hardware.