Technigma AI

Exploring open-source LLMs, local AI inference, model serving, quantization, and agentic AI. Particularly interested in benchmarking and optimizing models for real-world tool use, long-context workloads, and efficient inference across NVIDIA DGX Spark, Blackwell GPUs, and other local AI hardware. Experimenting with vLLM, GGUF, NVFP4/FP8, MoE models, AI agents, and practical GenAI infrastructure.