No description provided.

a GGUF parser that works on remotely hosted files

Self-learning LLM runtime — TurboQuant KV-cache (6-8x compression), SONA adaptive learning, FlashAttention, speculative decoding, GGUF inference

GGML-backed OCR addon for qvac (EasyOCR pipeline on GGUF weights)

application/x-gguf (GGUF local-LLM model) mimetype handler for plurnk-service. Parses the metadata header (arch/quant/context/tokenizer) without loading weights. Hand-rolled, no parser dependency.

llama.cpp gguf file parser for javascript

GGUF coder

In-process GGUF execution adapter for the Graphorin framework. Wraps node-llama-cpp@^3.5 to load .gguf model files directly into the same Node process - no daemon, no port to manage, no GPU contention with other processes. Declares trust: 'loopback' perma

a GGUF parser that works on remotely hosted files

Node.js bindings for SoulX-Singer-DiT GGUF inference (no dequantization, via modified llama.cpp)

wllama provider for @localmode - GGUF model inference via llama.cpp WASM with metadata inspection and browser compatibility checking

llama.cpp HTTP server provider for weaveIntel — local GGUF models via OpenAI-compatible API

Fine-tune any Hugging Face model on your own laptop using QLoRA, then export to Ollama-ready GGUF.

Pure hardware-fit engine for local GGUF models: will it fit this machine?

Native Node.js wrapper for llama.cpp with a lightweight GGUF model loader

GGUF editor

Standalone embedding recall benchmark for flair — run real recall numbers (p@3/MRR) against any GGUF embedding model, batch-compare, get a host-aware recommendation, and share redacted results. No flair install required.

LlamaCpp backend for RunAnywhere React Native SDK - GGUF model support for on-device LLM

C2PA manifest embedding for AI/ML model container formats: GGUF, SafeTensors, and ONNX

This package includes scripts to download the pre-trained model from huggingface, and convert the model to GGUF format as well.