FastFlowLM FastFlowLM
How It Works Models Benchmarks Demos Test Drive
Testimonials
Team Community News Roadmap
Docs
How It Works Models Benchmarks Demos Test Drive
Testimonials
Team Community News Roadmap
Docs
GitHub Discord Email

Docs

Models

Overview
Install

Instructions

Overview CLI Server Basics Open WebUI Microsoft AI Toolkit Obsidian RAG + LangChain Web Search + LangChain

Models

Overview LLaMA DeepSeek Qwen Gemma MedGemma GPT-OSS LFM Whisper EmbeddingGemma

Benchmarks

Overview LLaMA 3 Gemma 3 Qwen 3 GPT-OSS LFM2 1.2B

๐Ÿงฉ Models Overview

  • ๐Ÿ“‘ Detailed model cards are available โ€” explore the following model families
  • ๐Ÿš€ More models are on the way!
  • โœจ FLM supports full context length for all listed models!

๐Ÿ“š Model families

  • LLaMA
  • Qwen
  • Gemma
  • DeepSeek
  • gpt-oss
  • LiquidAI / LFM
  • Whisper
  • MedGemma
  • Embedding Gemma
FastFlowLM The leading LLM inference runtime for parallel NPU architectures

ยฉ 2025 FastFlowLM. All rights reserved.

Site

Technology Testimonials Company Docs

Connect

GitHub Discord Email