π§ FastFlowLM
NPU-only runtime for local LLMs
Fast, power-efficient, and 100% offline.
π§ͺ Test Drive (Remote Demo)
π Skip the setup β experience FastFlowLM instantly on a live AMD Ryzenβ’ AI 5 340 NPU with 32β―GB memory (more spec):
π Launch Now: https://open-webui.testdrive-fastflowlm.com/
π Login: guest@flm.npu
π Password: 0000
Real-time demo powered by FastFlowLM + Open WebUI β no downloads, no installs.
Upload your own.txt
files to test extended context prompts.
Try three optimized LLaMA models:llama3.2:1B
,llama3.2:3B
, andllama3.1:8B
β all accelerated on NPU.
π Note: Large prompts (30k+ tokens) may take longer on the 8B model β but it works. Try π Download a sample txt, containing over 38k token.
π Sections
π Installation
Quick 5βminute setup guide for Windows.
π οΈ Instructions
Run FastFlowLM using the CLI (interactive mode) or local server mode.
π Benchmarks
Real-time performance comparisons vs AMDβs official stack and other tools.
π§© Models
Supported models, quantization formats, and compatibility details.