IF YOU USE COMMUNITY QWEN MODELS DO NOT UPGRADE TO FLM v1.0.2+

Aquilia-mini-NPU2

FastFlowLM Q4NX conversion of XYZAILab/XYZ-Aquila-mini for AMD XDNA NPU inference.

This repository contains a quantized Q4NX port of the model, compiled for the FastFlowLM (FLM) runtime. It is not a GGUF file.

Item	Value
Source model	`XYZAILab/XYZ-Aquila-mini`
Source GGUF	`XYZAILab_XYZ-Aquila-mini-Q4_1.gguf`
Weights	`model.q4nx` (21.64 GB)
Modality	language
FLM version	`1.0.0`
Converted	2026-08-11

Source repository

Metadata from the upstream Hugging Face repository:

Item	Value
License	apache-2.0
Base model	`['Qwen/Qwen3.6-35B-A3B']`
Library	`transformers`
Model type	`qwen3_5_moe`
Pipeline	`image-text-to-text`
Downloads	2,091
Repo revision	`0cad6285baf6f37adf2c4e9696372c0140078fe0`

About

Q4NX for FastFlowLM (AMD Ryzen AI XDNA2) quant of https://huggingface.co/XYZAILab/XYZ-Aquila-mini

What is Q4NX?

Q4NX is FastFlowLM's native packed-quantization format - a rearranged Q4_1 layout tuned for the NPU matrix engine's tile sizes and memory access patterns. It is not a GGUF file and it does not run on llama.cpp or Ollama; it is meant exclusively for the FastFlowLM engine on AMD Ryzen AI NPUs.

Requirements

FastFlowLM >= 0.9.45 (flm CLI)
AMD Ryzen AI processor with XDNA2 (NPU2) - Strix Point / Ryzen AI 300 series or later
XRT NPU stack installed
32 GB of unified system memory (Q4NX weights + activations + KV cache)

Files

File	Purpose
model.q4nx	Quantized Q4NX weights
config.json	FastFlowLM model configuration
tokenizer.json	Tokenizer
tokenizer_config.json	Special tokens and chat template
chat_template.jinja	Chat template (optional)
flm-add.py	Installer script - registers this model with FastFlowLM

Install and run

This repository works with flm-add, a small installer that copies the model into the FastFlowLM user directory and registers the tag minicpm4.6:0.8b. It never modifies the system FastFlowLM install.

pip install flm-add or uv tool install flm-add

uv tool install flm-add
flm-add Atomic-Germ/Aquila-mini-35B-A3B-NPU2 --tag aquila-mini-moe:35b-a3b --family qwen3.6-moe
FLM_CONFIG_PATH="$HOME/.config/flm/model_list.json" FLM_XCLBIN_PATH="$HOME/.config/flm" flm run aquila-mini-moe:35b-a3b

Kernels

FastFlowLM's NPU kernels (xclbins) are closed source and are not shipped in this repository. flm-add.py links the kernels of the official qwen3.6-moe:35b-a3b model (Qwen3.6-35B-A3B-NPU2), because this model shares the same engine family (qwen3.6-moe) and architecture.