AI Model2026
Generates conversational and reasoning outputs with support for million‑token contexts; uses a hybrid attention + MoE design to cut long‑context inference FLOPs and KV cache. Suited for long‑document retrieval, coding and complex reasoning; MIT licensed.
AI Model2026
A vision-oriented foundation checkpoint for low-latency inference — DeepSeek V4 base in safetensors with FP8 optimizations. Designed for fast image generation and embedding use in inference pipelines; verify license and FP8/runtime compatibility before production use.
AI Model2026
Unifies multimodal image understanding, text-to-image generation, and instruction-based editing in a single diffusion LLM using a Mixture-of-Experts backbone, SigLIP-VQ discrete tokenizer, and a distilled diffusion decoder enabling fast (8-step) decoding; full-generation needs ~47GB GPU RAM.
AI Model2026
End-to-end multimodal model for native text↔image understanding, interleaved image-text generation, and image editing. Uses the NEO-Unify MoT architecture to avoid separate visual encoders/VAE. Suited for multimodal prototyping, demos, and research (Apache‑2.0).
AI Model2026
A 14B dense tri‑mode language model that supports autoregressive, diffusion‑based parallel decoding, and self‑speculation—designed to increase token throughput and acceptance length; best suited for researchers and engineers exploring decode‑efficiency tradeoffs on NVIDIA hardware under the Nemotron Open Model License.
AI Model2026
Provides an NVFP4-quantized 27B Qwen3.6 checkpoint optimized for faster, low-memory multimodal inference on 24GB GPUs. Includes MTP (multi-token prediction), extended 262k native context, and deployment recipes for vLLM/SGLang/KTransformers; best used with recommended backends for peak throughput.
AI Model2026
A Qwen-3.6 27B model variant optimized for DFlash (speculative decoding) to reduce generation latency and increase throughput. Focuses on faster inference on serving stacks and is suitable for text-generation endpoints where lower latency and resource efficiency matter.
AI Model2026
A GGUF-format preview checkpoint derived from Qwen3.6-27B — a multimodal, image-text-to-text reasoning model fine-tuned for more structured reasoning and consistent answer style; packaged for local inference and compatible with engines like vLLM/SGLang/llama.cpp.
AI Model2026
A 33B Mixture-of-Experts text-to-text model optimized for local, long-context agentic coding—3B activated params per token, 131k token window, mixed sliding-window and global attention, FP8 KV cache, Apache-2.0 license.
AI Video2026
Performs task-aware generative video restoration and editing in latent video space — restoration, super-resolution, watermark and subtitle removal — adapting LTX‑2.3 with IC‑Edit/IC‑LoRA adapters to prioritize temporal consistency and occlusion-aware reconstruction.
AI Model2026
Acts as the assistant (drafter) checkpoint for Gemma 4 26B A4B on Hugging Face, used in Speculative Decoding to pre-draft tokens and speed up generation. Designed for long-context, multimodal workflows where lower latency and on-device or edge inference matter.
AI Model2026
Unifies video, audio, image and text understanding for enterprise Q&A, summarization, transcription and document intelligence. The NVFP4 quantized variant reduces footprint to ~20.9GB for more efficient single‑GPU deployment and is tuned for NVIDIA runtimes (vLLM, TensorRT).