Downloads · 30 days
442
12% of all-time downloads
MiniCPM-V-4.6-NPU2
Atomic-Germ/MiniCPM-V-4.6-NPU2
MiniCPM-V-4.6-NPU2 is a image-text-to-text model from Atomic-Germ. Use it for the image-text-to-text task on the model card, and read the license before you ship it in a product. It is set up for q4nx. The card lists the license as other.
MiniCPM-V-4.6 is converted to Q4NX for hardware-accelerated inference with FastFlowLM on AMD Ryzen AI NPUs.
All-time downloads
3.8K
Public
Repo size
10.9 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.q4nx1.3 GB · 54%
At a glance
- Task
- Image-Text-to-Text
- Library
- q4nx
- License
- other
- Model type
- minicpmv4_6
- Access
- Public
- Created
- Aug 8, 2026
- Updated
- Aug 19, 2026
- SHA
- a1988886
Try a prompt
Base models
Model card
From the Hugging Face model README
IF YOU USE COMMUNITY QWEN MODELS DO NOT UPGRADE TO FLM v1.0.2+
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 (
flmCLI) - 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 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/MiniCPM-V-4.6-NPU2 --family qwen3.5 --tag minicpm-4.6:0.8b
FLM_CONFIG_PATH="$HOME/.config/flm/model_list.json" FLM_XCLBIN_PATH="$HOME/.config/flm" flm run minicpm-4.6:0.8b
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.q4nxsize: 1.03 GB- Base model: openbmb/MiniCPM-V-4.6-gguf
- License: other
GhostWriter Influence Test (Arbitrary but repeatable benchmark)
Tested on an AMD Ryzen AI 340 Framework 13 laptop.
| Metric | Value |
|---|---|
| Prompt Tokens | 9,210 |
| Completion Tokens | 631 |
| Total Tokens | 9,841 |
| Active KV Tokens | 9,841 |
| Max KV Token Capacity | 32,768 |
| KV Token Occupancy | 30.03% |
| Load Duration | 0.000000842 seconds |
| Prefill Duration (TTFT) | 7.58 ms |
| Decoding Duration | 21.44 ms |
| Prefill Speed | 1214.89 tokens/sec |
| Decoding Speed | 29.44 tokens/sec |
Original model card
See the upstream model card for training details, benchmarks, and upstream usage. This repository only contains the Q4NX conversion for FastFlowLM.
- Upstream card: openbmb/MiniCPM-V-4.6-gguf
- Task
- Image-Text-to-Text
- Library
- q4nx
- Type
- minicpmv4_6
- License
- other
- Languages
- en
- Created
- Aug 8, 2026
- Updated
- Aug 19, 2026