#gguf
5
2026-09-15
harshitkhandelwal208/hk
D
HK is a unified neural model format and framework built in native Zig, designed to replace SafeTensors, GGUF, and PyTorch checkpoints. Features zero-copy mmap loading, dual-mode quantization, 2:4 hardware sparsity, live model expansion, and 137+ architecture support with bindings for Python, Rust, Go, C#, Java, and TypeScript.
2026-10-23
Show HN: Train LoRA directly on the GGUF you have, then merge the adapter
unrated
Use the same GGUF you serve, merge the adapter back into it and then use the same engine to run the model, all in all a "LLM Toolbox"
2026-10-02
kouhxp/gutsy
unrated
Local decision model with calibrated probabilities: send a state and yes/no, choice or score questions, get a probability for every option. 0.8B GGUF on CPU, Jev-style API.
2026-08-31
alphaparkinc/genpark-multi-architecture-low-bit-quantization-compiler-skill
unrated
Multi-architecture low-bit quantization compiler for GGUF kernels (Llama.cpp style)
2026-08-31
alphaparkinc/genpark-multi-backend-quantized-model-loader-playground-skill
unrated
Multi-backend quantized model loader supporting GGUF & EXL2 (Oobabooga style)