thetom-ai author hub

Nemotron H 8B Base 8K — Config I TQ4 1S GGUF First Config I / tq4 1s quantization of a Nemotron H Mamba 2 hybrid model. This is a TurboQuant https://github.com/TheTom/llama cpp turboquant Config I weight quantization TQ4 1S — RHT/Walsh Hadamard rotated 4 bit, 16 level Lloyd Max …