AI Audio2025
Generates full songs from lyrics and style prompts by first writing an editable melody-and-chord score and then rendering vocals and accompaniment. Unifies symbolic planning and audio synthesis in one pipeline, enabling readable score inspection, zero‑shot covers, and agent-driven editing.
AI Model2026
Performs one-shot, long-horizon OCR parsing of multi-page documents by using Reference Sliding Window Attention (R‑SWA) to keep the KV cache constant, enabling single-pass transcription of dozens of pages. Key features: constant KV cache, DeepEncoder visual compression, MoE-backed 3B model—suited for large-scale PDF/image parsing on GPU.
AI Image2026
Provides multiple quantized releases (GGUF, safetensors, MLX) of Qwen-Image-2.1 for local text-to-image generation; includes GPU- and Apple-Silicon–optimized quantizations, companion text encoders/VAEs, and recommended ComfyUI configurations.
AI Model2026
Post-trained multimodal Qwen3.8-27B variant that uses alternating SFT and RLOO to reduce pathological long reasoning tails; ships multiple quantization tiers (BF16, FP8, NVFP4, INT8, INT4, GGUF), supports MTP and DFlash2 speculative decoding, and includes detailed benchmark and runtime recommendations.
AI Model2026
GGUF (llama.cpp) quantized build of MiniCPM‑V 4.7 35B‑A3B for local/CPU and on-device multimodal image/video→text inference; supports imatrix mixed quantization, Lookahead Expert Scheduling and DSpark speculative decoding to reduce expert-loading stalls and improve throughput.
AI Model2026
Text-only sparse Mixture-of-Experts language model for long-context reasoning, coding, and agentic tool use; 501B total / ~23B active parameters, 1M-token context, and BF16/FP8/NVFP4 checkpoints released under Apache 2.0.
AI Image2026
Generates images from natural-language prompts or structured JSON layouts, fine-tuned from a 5B backbone to improve bilingual long-text rendering and layout control; runs via a Diffusers pipeline and expects PyTorch + an NVIDIA GPU.
AI Model2026
Generates calibrated decisions (choice/score/noul) from a prompt and optional images, up to 256 options. Routed MoE experts are quantized to NVIDIA NVFP4 to reduce weights to ~25.6 GB and GPU memory to ~23.3 GiB; provided as a vLLM-compatible System 1 decision model with a /v1/decide endpoint.
AI Model2026
A System 1 multimodal decision model that picks among up to 256 options and returns calibrated probabilities for choice, yes/no and 0–5 score decisions from text and images. Fine-tuned on Qwen3.5-35B-A3B, available in bf16 and NVFP4 builds (NVFP4 fits ~23.3 GiB GPU), and served via vLLM's POST /v1/decide API.
AI Model2026
Generates images from natural-language prompts or structured JSON layouts, emphasizing readable long-form bilingual text and precise layout control. Built on a compact 5B diffusion backbone, supports prompts up to 4K tokens and ships as a Diffusers pipeline under Apache‑2.0.
AI Model2026
Quantized multimodal vision-language model for reasoning, coding, tool use, document and video understanding; 120B total (12B active) with NVFP4 quantization, native Multi-Token Prediction for speculative decoding, and up to 1M-token context — designed for deployment on NVIDIA GPU stacks.
AI Image2026
Open-weight 5.6B FLUX.3 image model for text-to-image and multi-reference image editing with pixel-accurate bounding-box layout control. Ships distilled (fast, low-step) and base (fine-tuneable) checkpoints and runs on consumer GPUs down to an RTX 3090.