⚡ FastFlowLM (FLM) — Unlock Ryzen™ AI NPUs
Run large language models — now with Vision, Audio, Embedding and MoE support — on AMD Ryzen™ AI NPUs in minutes.
No GPU required. Faster and over 10× more power-efficient. Support context lengths up to 256k tokens.
Ultra-Lightweight (16 MB). Installs within 20 seconds.
📦 The only out-of-box, NPU-first runtime built exclusively for Ryzen™ AI.
🤝 Think Ollama — but deeply optimized for NPUs.
✨ From Idle Silicon to Instant Power — FastFlowLM Makes Ryzen™ AI Shine.
🔽 Download 📊 Benchmark 📦 Models
🧪 Test Drive 💬 Discord
FLM in Action — Fast and Ultra-Efficient
Runs GPT-OSS-20B at 19 TPS (token per second) with 10× GPU efficiency — the fastest MoE on any NPU.
Transcribe hours of audio locally — FLM runs OpenAI Whisper fully on the NPU — fast, private, and efficient.
Runs Meta Llama 3.2-3B at 28 TPS with over 10× GPU efficiency — the fastest on any NPU.
Why FastFlowLM (FLM)?
🧠 No Low-Level Tuning Needed
Run your models without worrying about NPU internals — FLM handles all the hardware-level optimization.
🧰 Ollama Simplicity — Optimized for Ryzen™ AI NPUs
Same CLI/API workflow developers love, but deeply optimized for AMD’s Ryzen™ AI NPU architecture.
💻 Free Your GPU & CPU
FLM runs entirely on the Ryzen™ AI NPU, leaving the rest of the system free for other workloads.
📏 Full Context Lengths
All FLM models support the maximum context length — up to 256k tokens — enabling long-form reasoning.
About the Company
FastFlowLM Inc. is a startup developing a runtime with custom kernels optimized for AMD Ryzen™ AI NPUs, enabling LLMs to run faster, more efficiently, and with extended contexts — all without GPU fallback. FLM is free for commercial use up to USD 10 million in annual company revenue.
📩 Contact: info@fastflowlm.com