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
Base image-generation foundation model tuned for visual search and prompt-guided synthesis, intended as a compact starting point for local inference or fine-tuning. Emphasizes easy integration into image pipelines and suitability for downstream adaptation.
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
High-resolution vision transformers pretrained on one billion human images for human-centric tasks such as pose estimation, body-part segmentation, surface-normal and pointmap prediction. Provides multiple backbone sizes and task-specific checkpoints; released under the Sapiens2 license.
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 Model2026
Provides a lightweight assistant (draft) model for Gemma 4 E4B used in speculative-decoding pipelines — it predicts token drafts that the target model verifies in parallel, enabling up to ~2× decoding speedups while preserving identical final outputs. Useful for low-latency, multimodal assistant and on-device scenarios.
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.