Tag: #rx7900xtx

Run 125B AI Models Locally with Strata: Bye Bye 27B

Strata runs the 125B Qwen3.8-Flash-Next model on a normal gaming PC by splitting it across VRAM and system RAM. Install on Windows and Linux, watch the Monitor tab, and connect it to the Pi coding agent.

2026-10-17 llm strata qwen moe local-ai coding-agent pi amd rx7900xtx linux windows
Muse Glimmer 30B by Meta: The Best Local Coding Agent?

Install Muse Glimmer 30B from Meta with llama.cpp, speed it up with DFlash speculative decoding, and connect it to the Pi coding agent.

2026-08-20 llm llama-cpp meta muse-glimmer local-ai coding-agent pi amd rx7900xtx draft-model
Installing Llama.cpp on Windows 11 (AMD & Nvidia)

Install Llama.cpp on Windows, pick the right GPU build (CUDA or Vulkan), and run your first LLM with llama-server.

2026-07-05 llm llama-cpp windows gpu amd rx7700xt rx7800xt rdna3 rx7900xtx vulkan