Model catalog
Choose a recipe
FastFlowLM curates the most requested families and publishes tuned manifests under flm pull <model>.
We validate every build on Ryzen™ AI laptops and provide matching cards—see them here.
The catalog already covers 22 models spanning Gemma-3 (Vision), Qwen3, GPT-OSS 20B (MoE), DeepSeek-R1, Whisper
(Audio), MedGemma, and other leading open families.
Supported families
Each manifest describes quantization, context window, tokenizer, and recommended memory, so there are no surprises after download.
Llama 3.x
Gemma 3 (Vision)
DeepSeek R-1
Qwen 3 (Vision)
GPT-OSS (MoE)
LFM2 (Liquid AI)
EmbeddingGemma (RAG)
Whisper (Audio)
MedGemma
xLAM-2 (Tool-calling, Salesforce), and their corresponding Chat Templates and major API (e.g., OpenAI-compatible API)
Roadmap
Upcoming drops
Follow the GitHub project for rolling releases. We publish nightly builds for community testing and stable channels every few weeks.
-
Fill this in
Coming soon!