AI Model2026
Performs feed‑forward streaming 3D reconstruction from image sequences, combining coordinate grounding, dense geometric cues and trajectory memory to correct long‑range drift; uses paged KV‑cache attention for ~20 FPS inference at 518×378 and supports sequences >10,000 frames.
AI Model2026
Drafts multiple tokens in parallel with a lightweight block-diffusion drafter to enable speculative decoding for faster LLM inference. Designed to pair with Qwen3.6-35B-A3B and reports up to ~2.9× throughput improvements on common benchmarks.
AI Model2026
A healed 64-layer 'frankenmerge' that stacks two Qwen3.5-derived finetunes into an ~18B GGUF model for multilingual text generation, reasoning, and reliable code/frontend output. Healed with a 1000-step QLoRA to reduce layer-boundary artifacts and targeted to run on 12–16 GB GPUs.
AI Model2026
Detects and masks personally identifiable information (PII) in text using a bidirectional token-classification model for high-throughput, on‑premises sanitization. Key traits: 1.5B parameters, 128k-token context, Apache 2.0 license, and tunable precision/recall operating points.
AI Model2026
An uncensored, fully unlocked GGUF port of Qwen 3.6‑35B‑A3B for local multimodal (text+image) inference, offering K_P 'Perfect' quant variants (Q8–Q2) and an mmproj for vision. Suited for offline research and experimentation; not for use-cases requiring safety filters.
AI Model2026
GGUF quantized files for a Qwen3.6-35B checkpoint fine-tuned with Claude Opus 4.6-style chain-of-thought distillation to improve reasoning. Offers multiple llama.cpp-compatible quant options (Q4/Q5/Q6/Q8) for local text-generation inference.
AI Model2026
Fine-tuned Qwen3.6-35B-A3B MoE that reproduces Claude Opus 4.7-style chain-of-thought with explicit <think>…</think> blocks. Offers sparse activation (256 experts, ~3B active params), 64k context, and GGUF builds for local inference; best for long, multi-step reasoning but may emit very long reasoning traces.
AI Model2026
Provides a GGUF-packaged, native-INT4 quantized build of the multimodal Kimi K2.6 model for image-text-to-text inference — packaged for local/self-hosted inference engines (vLLM, SGLang, KTransformers) to reduce footprint while keeping multimodal capabilities.
AI Model2026
Unified multimodal LLM for enterprise workflows: ingests video, audio, image and text to perform transcription, OCR, Q&A, summarization and long-context reasoning. Provides BF16/FP8/NVFP4 weights and integrations with vLLM, TensorRT-LLM and other runtimes.
AI Model2026
Produces 384‑dim multilingual (and code) embeddings with up to 32,768 token context, optimized for low‑latency production retrieval. Compact 97M model with ONNX/OpenVINO and vLLM/GGUF deployment options for edge and high‑throughput use.
AI Infra2026
Provides high-performance CUDA/CUTLASS kernels implementing Kimi Delta Attention (KDA), accelerating KDA prefill on SM90+ (Hopper) GPUs. Integrates as a drop-in backend for flash-linear-attention, supports native variable-length batching, and targets K=V=128; requires CUDA 12.9+/PyTorch 2.4+.
AI Model2026
A 27B multimodal causal language model with a vision encoder and native long-context support (262,144 tokens). Optimized for repository-level coding agents and multimodal understanding; includes preserved "thinking" traces, multi-token prediction (MTP), and deployment recipes for vLLM / SGLang / Transformers.