MiniCPM-V-4.6 - Q4NX for FastFlowLM (AMD Ryzen AI XDNA2)
MiniCPM-V-4.6 is converted to Q4NX for hardware-accelerated inference with FastFlowLM on AMD Ryzen AI NPUs.
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 (
flm
CLI)
AMD Ryzen AI processor with
XDNA2 (NPU2)
- Strix Point / Ryzen AI 300
series or later
Linux with the XRT NPU stack installed
~8 GB of unified system memory (Q4NX weights + activations + KV cache)
Files
File
Purpose
model.q4nx
Quantized Q4NX text weights
config.json
FastFlowLM model configuration
tokenizer.json
Tokenizer
tokenizer_config.json
Special tokens and chat template
chat_template.jinja
Chat template (optional)
README.md
flm-add.py
Installer script - registers this model with FastFlowLM
Install and run
This repository ships
flm-add.py
, 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.
# one-time environment (add these to ~/.bashrc)export FLM_CONFIG_PATH="$HOME/.config/flm/model_list.json"export FLM_XCLBIN_PATH="$HOME/.config/flm"
git lfs install
git clone https://huggingface.co/Atomic-Germ/MiniCPM-V-4.6-NPU2
cd MiniCPM-V-4.6-NPU2
python3 ./flm-add.py .
flm run minicpm4.6:0.8b
Run
python3 ./flm-add.py --help
for all options. Without a clone, the same
command works against the repo id directly:
FastFlowLM's NPU kernels (xclbins) are closed source and are not shipped in this repository. This model uses the
qwen3.5
engine family and is shape-identical to the official
qwen3.5:0.8b
model (
Qwen3.5-0.8B-NPU2
). Point the runtime's xclbin path at the matching
xclbins
directory (or ship your own) before running.
MiniCPM-V-4.6-NPU2 huggingface.co is an AI model on huggingface.co that provides MiniCPM-V-4.6-NPU2's model effect (), which can be used instantly with this Atomic-Germ MiniCPM-V-4.6-NPU2 model. huggingface.co supports a free trial of the MiniCPM-V-4.6-NPU2 model, and also provides paid use of the MiniCPM-V-4.6-NPU2. Support call MiniCPM-V-4.6-NPU2 model through api, including Node.js, Python, http.
MiniCPM-V-4.6-NPU2 huggingface.co is an online trial and call api platform, which integrates MiniCPM-V-4.6-NPU2's modeling effects, including api services, and provides a free online trial of MiniCPM-V-4.6-NPU2, you can try MiniCPM-V-4.6-NPU2 online for free by clicking the link below.
Atomic-Germ MiniCPM-V-4.6-NPU2 online free url in huggingface.co:
MiniCPM-V-4.6-NPU2 is an open source model from GitHub that offers a free installation service, and any user can find MiniCPM-V-4.6-NPU2 on GitHub to install. At the same time, huggingface.co provides the effect of MiniCPM-V-4.6-NPU2 install, users can directly use MiniCPM-V-4.6-NPU2 installed effect in huggingface.co for debugging and trial. It also supports api for free installation.