Add it to a GitHub README or profile β the card updates as the ranking changes:
Run Gemma-4-31B at full 256K context on a $1,400 AMD RDNA4 GPU (gfx1201): TurboQuant KV cache + HIP-graph-safe Flash-Attention for llama.cpp, fully measured on real hardware.
Fine-tune your own LLM on an AMD Radeon GPU β the easy, tested way. QLoRA via ROCm on Windows/WSL2 & Linux, a worked Gemma-4 example, a reusable live training dashboard, and a smoke test that proves the loss falls.
Usability benchmark for local LLMs on AMD hardware (RDNA4 + Strix Halo) β agentic throughput, self-repair counts and context-depth decay, all parsed from llama.cpp server logs