llama.cpp fork for significantly improved performance on Ampere generation Nvidia cards (especially RTX 3090 / 3090 Ti): example: 110+ tok/s over a 100K-token generation at temperature 1 for qwen3.8, supporting full 262K ctx. Supports low memory (12gb) configs for 200k+ ctx. 120+ TPS, 3300+ prefill for QFN 3.8.
- ampere
- consumer-gpu
- cuda
- ggml
Pathology Language and Image Pre-Training (PLIP) is the first vision and language foundation model for Pathology AI (Nature Medicine). PLIP is a large-scale pre-trained model that can be used to extract visual and language features from pathology images and text description. The model is a fine-tuned version of the original CLIP model.
Private, provider-neutral context compression for LLMs. Reversibly compress schemas and logs inside your perimeter with zero third-party calls.
- cli
- compression
- context-window
- cost-reduction
Pure-Rust LLM inference engine for GGUF (Qwen, DeepSeek, GLM, Hy4, Flint). Runs models bigger than your VRAM on CUDA and Vulkan, with MTP drafts and an OpenAI/Anthropic server. 12 GB RTX 3060 vs llama.cpp: Qwen3.6-35B-A3B UD-Q5_K_M 80.5 vs 64.4 tok/s, Flint UD-Q5_K_XL 64.6 vs 48.6. With MTP: 108 tok/s (UD-Q3_K_M), up to 160 (UD-Q2_K_XL).
C++/CUDA single-GPU inference engine for Qwen3.8 (incl. Qwen3.8-Flash-Next with offloaded experts) on the RTX 5090; grew from NInfer
Capri — an AI desktop companion for Windows with local/API models, Hugging Face, optional voice, memory and permission-based desktop tools.
Extract knowledge from all information sources using gpt and other language models. Index and make Q&A session with information sources.
Local-first web & document ingestion engine in Rust — HTTP/browser capture, layout-aware PDF/Office/OCR parsing, persistent sync, verifiable data graphs, and evidence-grounded AI context.
9RouterX (9R Next Go Generation): Single-binary Go AI router, LLM gateway & 20-40% token saver. Route Claude Code, Cursor & Codex across 155 providers, 28 OAuth & 248 free models (24 keyless) — OpenAI, Claude, Gemini, DeepSeek, Groq, Ollama & MCP.
Find known secrets in your AI coding agent sessions (Claude Code, Codex, Cursor), then guard the next one with local hooks that trace risky commands to the content that dictated them. Open source, no telemetry.
Fast local LLM inference for the GPU you already have: one Rust binary, GGUF models, an OpenAI-compatible server and a chat page with a ghost.
TranslatedChinese edition of an AI reference image gallery | Costumes (1,407 realistic sets / 1,320 animation sets), 1,499 face shapes, 1,439 pose line drawings and 1,439 depth maps, 843 anime-style (二次元) entries. Designed for AI painting, character design, and comic-drama storyboards, with support for Chinese search, multi-angle browsing, and image copying and downloading. Open-source static site that preserves the original sources and terms of use.
- ai-art
- ai-comics
- art-reference
- character-design
Local AI in .NET, with no Python sidecar and no API key: embeddings, entity extraction, image and video search and chat on ONNX Runtime (CPU/CUDA), through Microsoft.Extensions.AI.
Serum 2 2026 standalone bundle with full plugin suite, multitrack editor, bundled instruments and portable offline mode for Windows 11
SVGFaith: a two-layer meta-evaluation of faithfulness metrics for text-to-SVG generation
140 curated Seedance 2.5 Flash video prompts with preview frames, grouped by use case.
- ai-video
- ai-video-generation
- apimart
- awesome
On-device Vision Model - a fully offline, free vision pipeline that gives text-only models (e.g. DeepSeek) image understanding and multilingual OCR through an OpenAI-compatible local API. Only tokens are needed: no API key, no subscription, no cloud cost. Recommended for native speakers of Chinese, English, Japanese and Korean.
PROMETHEVS: run the full DeepSeek-V4.1-Flash-1017 (510 GB) on a gaming PC with 64 GB RAM and a 12 GB GPU. PROMETHEVS engine (compress-then-correct), OpenAI-compatible local server, report and logs.
project on fine-tuning qwen to generate text w/o letter 'e'
Sınırsız Foto: Z-Image-Turbo (Q8_0, full quality) on a 4 GB GTX 1050 Ti laptop with 16 GB RAM. stable-diffusion.cpp + cuDNN VAE, Windows, every number measured. Unofficial. Not affiliated with Tongyi-MAI, leejet or NVIDIA.
LLM-powered Text-to-SQL evaluation toolkit: schema ingestion, retrieval eval, and standalone SQL judge/re-scorer.
PocketStrike is a privacy-first mobile AI workstation. It combines zero-cloud native on-device GGUF inference (ARM NEON accelerated) │ with frontier cloud LLMs, multi-step ReAct agent tools, Model Context Protocol (MCP) servers, self-evolving cross-session memory, and FLUX neural image │ generation.
DeepWrite AI is Made with the Help of ChatGPT3 and Specific Model is Prepared for Generating Perfect Blog Post with atmost Clarity. This is Just the Version 1.0 More Improvement Will be Implemented.
- ai
- api
- chatgpt3
- fullstack-development
Integrates AI tools into Microsoft Word