AI Model2026
A GGUF-quantized build of Qwen3.6-35B packaged by unsloth for local and accelerated inference. Adds MTP speculative decoding guidance and deployment notes for llama.cpp, vLLM, SGLang and long-context/multimodal use cases.
AI Model2026
Generates production-ready offensive-security artifacts from prompts—Nuclei templates, CVE PoCs, exploit scripts and pentest tooling—fine-tuned on bug-bounty reports and CVE writeups and quantized for consumer/server GPU deployment.
AI Model2026
Multilingual streaming ASR that transcribes 40 language-locales using a cache-aware FastConformer‑RNNT architecture. Supports language-ID prompting (or auto-detect), punctuation/capitalization, and configurable chunk sizes to trade latency vs. accuracy for production transcription and streaming voice agents.
AI Model2026
Provides a locally runnable 26.9B Qwen3.6 checkpoint that surgically reduces refusal behavior in weight space while preserving capability; ships bfloat16 safetensors and a GGUF quant ladder for local runtimes and red-team evaluation.
AI Model2026
A ternary-weight (~1.58-bit) 4B text-to-image diffusion transformer optimized for NVIDIA GPUs using Gemlite INT2 and HQQ; it reduces the transformer to ~1.21 GB (4.55 GB CUDA payload) and targets 1024×1024 generation with a 4-step FlowMatch-Euler sampler.
AI Model2026
Processes images and text to produce structured, reasoning-rich text outputs for high-throughput agentic workflows. Sparse MoE design (198B total, ~11B active per token), 256k context window and selectable reasoning levels—optimized for single-pass parsing, verification, and multi-step automation.
AI Model2026
Performs fast, high-quality vision–language grounding: given an image plus a natural-language prompt it returns bounding boxes or points for referred objects. Uses Parallel Box Decoding for parallel coordinate prediction (higher throughput) and targets research/non-commercial use.
AI Model2026
Performs image-to-text document parsing and OCR for complex elements (tables, formulas, charts, seals), with multilingual support (en/zh). It uses region-aware data optimization and progressive post-training to improve weak-region supervision and is plug-and-play compatible with PaddleOCR-VL-1.5.
AI Model2026
Quantized NVFP4 build of the Qwen3.6-35B MoE language model, optimized with NVIDIA Model Optimizer to cut model size and GPU memory by ~3.06× for inference. Designed for vLLM and NVIDIA GPU deployments (Hopper/Blackwell).
AI Model2026
Hybrid LFM2.5 text-generation model optimized for on-device assistants and agentic workflows — 8.3B total / 1.5B active parameters with 131,072-token context. Prioritizes low-latency, high-throughput inference and multilingual instruction-following; not optimized for pure heavy programming or knowledge-heavy QA without retrieval.
AI Video Papers2026
Performs training-free early-stage visual token compression inside the vision encoder to cut time-to-first-token (TTFT) and FLOPs for Video-LLMs. Introduces a decoupled spatial token selection strategy and reports up to 2.65× TTFT reduction and 61% FLOPs savings on LLaVA-OneVision-7B (NVIDIA A100) while preserving full-token accuracy — aimed at latency-sensitive video understanding.
AI Model2026
GGUF quantizations of Step-3.7-Flash: a sparse multimodal Mixture-of-Experts LLM with native image understanding, selectable reasoning levels, and a 256K context window. Ships multiple calibrated Q3/Q4/IQ quant files plus an mmproj vision projector for local llama.cpp inference on high-memory hosts.