Ornith-1.0-35B-ROCmFPX is a high-performance 35B mixture-of-experts model quantized and tuned specifically for local multi-agent workloads on AMD Ryzen AI Max+ 395 / Strix Halo (Radeon 8060S) using Vulkan and ROCmFPX. > Note: ROCmFPX and ROCmFP4 GGUF models use custom experimental block tensor layouts. Standard stock llama.cpp, Ollama, or LM Studio cannot load ROCmFPX GGUFs out of the box. To run these GGUF quants: 1. Use the Bundled Launcher: Use python3 runserver.py or ./run.sh from the GitHub Repository which ships with pre-compiled ROCmFPX Vulkan binaries. 2. Build from Source: Or build llama-server` from the specialized ROCmFPX Fork. OpenAI-compatible API endpoint will be live at http://127.0.0.1:8089/v1.
Модальности:
Генерация текста
Области применения:
Диалог / чат
Задача: Генерация текста
Автор: julianmb
Теги: gguf, rocmfpx, strix-halo, amd-ryzen-ai-max, tool-calling, agent, multi-agent, en
Лайков: 3 | Загрузок: 284
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
