gguf

A web-based memory usage and performance calculator for Huggingface GGUF models

Instruction Fine-Tuning of Meta Llama 3.2-3B Instruct on Kannada Conversations. Tailoring the model to follow specific instructions in Kannada, enhancing its ability to generate relevant, context-aware responses based on conversational inputs. Using the Kannada Instruct dataset for fine-tuning! Happy Finetuning 🎋

A TUI around llama.cpp for running, managing, and benchmarking local GGUF models and launching the pi coding agent against your local server.

Deterministic, read-only static auditor for GGUF models: behavioral chat-template backdoors + SSTI, tokenizer, config, and model-card surfaces - never renders, never loads weights. 192,032 repos, 137,698 templates analyzed, 0 reviewed false-positive FAILs.

Local AI workstation — discover, run, chat, benchmark, and generate images from open-weight models. DFlash/DDTree speculative decoding, TurboQuant & TriAttention cache compression strategies, MLX + llama.cpp + vLLM + MTPLX backends.

Run and manage both vLLM and llama.cpp model servers from one terminal UI + CLI — shared Docker Compose profiles, live tok/s, and cross-backend port/GPU conflict checks. NVIDIA + Linux.

Locally fine-tuned Russian RAG models: document splitter, query expansion, retrieval embedder. Teacher distillation → GGUF → llama.cpp on AMD Vulkan. Commercial-OK licenses.

Rivo Agent is a private, local-first mobile AI assistant that runs compact GGUF language models directly on your phone. It lets users download a compatible model, chat offline, keep local memory, customize assistant behavior, and use AI privately without sending conversations to a remote inference server.

CPU-first, eager-execution tensor/autograd runtime and LLM inference engine written in pure Zig

​LedgerMind — an autonomous living memory for AI agents. It self-heals, resolves conflicts, distills experience into rules, and evolves without human intervention. SQLite + Git + reasoning layer. Perfect for multi-agent systems and on-device deployment.

Hugging Face Model downloader and GGUF Converter.

Arabic-first expressive zero-shot speech synthesis — Audar-TTS-V1 (Flash + Turbo + Pro). Voice cloning, expression tags, benchmarks, technical report & inference.

CLI wrapper for llama.cpp providing an ollama-like experience

Local AI model manager

Run Ornith, Qwen, Nemotron & DeepSeek optimized on AMD Strix Halo — unified OpenAI-compatible server with tuned ROCmFP4 quants, validated 262K context, vision support & hot-swap model zoo (iGPU + NPU)

豆芽 Douya — 基于 llama.cpp 的隐私优先本地 AI 桌面助手 · 完全离线 · 多后端(CUDA/HIP/SYCL/Vulkan/OpenVINO/CPU) · GPU 加速 · 多模态 · RAG · OpenAI 兼容 API

Lna-Lab production pipeline: GGUF -> modelopt-format NVFP4 + working MTP head for vLLM on RTX PRO 6000 Blackwell (SM120). Stages 2 (NVFP4) and 3 (MTP graft) are Lna-Lab originals; stage 1 (GGUF->bf16) reuses li-yifei/gguf-to-nvfp4.

Persistent local memory engine for OpenClaw — replaces default memory-system with a full context lifecycle: hybrid vector recall, automatic compaction, and domain-adaptive gating over LibraVDB