Docker Compose for llama.cpp GGUF servers on AMD Strix Halo: Qwen, Gemma, and Laguna packages (abliterated and quantized), stock Vulkan plus ROCmFP4/MTP and ROCmFPX, parallel slots, with prefill/decode and quality metrics measured on this rig.
vulkan benchmarks mtp gemma heretic rocm uncensored quantized laguna llama-cpp qwen gguf strix-halo gfx1151 abliterated qwen3-6 obliterated rocmfp4 rocmfpx
-
Updated
Jul 29, 2026 - Python