Embodied AI2026
Provides a portable C++ inference runtime to deploy embodied AI models (vision–language–action and world–action) on heterogeneous robot hardware, enabling latency-first batch-1 closed-loop control. Key features include modular multi-rate layers, fused low-latency inference, and extensible head/IO plugins.
AI Model2026
Provides a large Mixture-of-Experts instruct LLM (295B total parameters, 21B active, 256K context) optimized for reasoning, long-context retention and agent workflows; open-sourced under Apache-2.0.
AI Model2026
Provides GGUF-quantized local-deploy weights for a 1B MiniCPM5-derived conversational LLM, embedding a 'thinking' chat template and supporting up to 128K-token context; ships Q4/Q5/Q8/F16 quant files (Q8_0 recommended) for llama.cpp, Ollama, and LM Studio.
AI Model2026
A 1B-parameter 'Thinking' language model fine-tuned on Fable 5 to improve coding and instruction-following; supports chain-of-thought style outputs, XML tool-call format, and up to 128K-token context, with GGUF builds for single-GPU local deployment.
AI Model2026
Instruction-tuned compact conversational model (Qwen3-4B-based) that generates short, chat-style replies and is optimized to run on a single mid-range GPU. Uses ChatML prompts, bfloat16 safetensors and is released under Apache-2.0; the model card notes a joke/placeholder disclaimer.
AI Video2026
Generates short videos that preserve a reference person's identity from a single reference image as a LoRA adapter for LTX-2. Uses overlap reference conditioning with TASS‑RoPE source-phase tagging and an ArcFace identity loss; runs in ComfyUI via BFS Nodes and supports a 4‑panel character‑sheet mode for clothing/body consistency.
AI Model2026
Decides whether a user prompt should be executed locally on an edge small LLM or routed to a larger cloud model, emitting a deterministic pipe-separated decision string. A 51.7M micro-LLM fine-tuned with multi-task sequence generation to predict domain, complexity and code/math flags, optimized for ultra-low latency edge routing.
AI Model2026
Fine-tuned variant of Qwen3.6-27B that cuts internal reasoning (‘thinking’) token usage by roughly 46% on average while preserving benchmark accuracy and safety behavior. Targets lower latency and inference cost; ships on Hugging Face with GGUF quantizations for local use.
AI Model2026
Deployment-optimized hybrid MoE LLM (75B total / 9.3B active) produced via Iterative Puzzle compression and Multi-Token Prediction to double server throughput and raise single-GPU concurrency; designed for multilingual reasoning, long-context generation, and high-volume agentic/chat deployments.
AI Model2026
27B multimodal LLM post-trained to prioritize agentic, weight-scaled reasoning over 64K-token contexts. Built on Qwen3.6-27B and released with BF16 weights plus several GGUF quants; aimed at coding, long-document reasoning, tool use and multimodal inspection.
Expresses diverse computer-vision tasks as instruction-driven text, image, or mixed generation from a single unified multimodal model, producing outputs for detection, segmentation, depth, pose, OCR and more. Trained on a converted SenseNova‑Vision instruction–response corpus and requires no task-specific prediction heads.
Introduces KronQ, a post-training quantization framework that incorporates gradient covariance via a Kronecker‑factored Hessian to guide input/output weight rotations and sensitivity-driven mixed-precision allocation. Demonstrates stable 2-bit weight-only quantization on LLaMA-3-70B (7.93 PPL).