Atomic-Germ / MiniCPM-V-4.6-NPU2

huggingface.co
Total runs: 521
24-hour runs: 2
7-day runs: -31
30-day runs: -2.5K
Model's Last Updated: August 20 2026
image-text-to-text

Introduction of MiniCPM-V-4.6-NPU2

Model Details of MiniCPM-V-4.6-NPU2

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:

python3 ./flm-add.py Atomic-Germ/MiniCPM-V-4.6-NPU2

If the model has not been published yet, deploy the local directory with the converter instead:

python convert.py -i <source.gguf> -o <this directory> -d minicpm4.6:0.8b --deploy-name "MiniCPM-V-4.6-NPU2"
Kernels

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.

Serve (OpenAI-compatible)
flm serve minicpm4.6:0.8b --port 8080
curl http://127.0.0.1:8080/v1/chat/completions \
  -H 'Content-Type: application/json' \
  -d '{"model":"minicpm4.6:0.8b","messages":[{"role":"user","content":"Hello!"}],"max_tokens":256}'
Model
  • Registry tag: minicpm4.6:0.8b
  • Engine family: qwen3.5
  • Kernel source: official qwen3.5:0.8b ( Qwen3.5-0.8B-NPU2 )
  • Context length: 262,144 tokens (from config)
  • Hidden size: 1024
  • Layers: 24
  • Intermediate size: 3584
  • Vocabulary: 248094
  • model.q4nx size: 1.03 GB
  • Base model: openbmb/MiniCPM-V-4.6-gguf
  • License: other
Original model card

See the upstream model card for training details, benchmarks, and upstream usage. This repository only contains the Q4NX conversion for FastFlowLM.

Runs of Atomic-Germ MiniCPM-V-4.6-NPU2 on huggingface.co

521
Total runs
2
24-hour runs
-12
3-day runs
-31
7-day runs
-2.5K
30-day runs

More Information About MiniCPM-V-4.6-NPU2 huggingface.co Model

More MiniCPM-V-4.6-NPU2 license Visit here:

https://choosealicense.com/licenses/other

MiniCPM-V-4.6-NPU2 huggingface.co

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 Url

https://huggingface.co/Atomic-Germ/MiniCPM-V-4.6-NPU2

Atomic-Germ MiniCPM-V-4.6-NPU2 online free

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:

https://huggingface.co/Atomic-Germ/MiniCPM-V-4.6-NPU2

MiniCPM-V-4.6-NPU2 install

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.

MiniCPM-V-4.6-NPU2 install url in huggingface.co:

https://huggingface.co/Atomic-Germ/MiniCPM-V-4.6-NPU2

Url of MiniCPM-V-4.6-NPU2

MiniCPM-V-4.6-NPU2 huggingface.co Url

Provider of MiniCPM-V-4.6-NPU2 huggingface.co

Atomic-Germ
ORGANIZATIONS

Other API from Atomic-Germ