Downloads · 30 days
169
8% of all-time downloads
Atomic-Germ/DynaGuard-8B-NPU2
DynaGuard-8B-NPU2 is a text generation model from Atomic-Germ. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as apache-2.0.
FastFlowLM Q4NX conversion of tomg-group-umd/DynaGuard-8B-NPU2 for AMD XDNA NPU inference.
Downloads · 30 days
169
8% of all-time downloads
All-time downloads
2.2K
Public
Repo size
15.3 GB
Likes
0
Public
Click a slice to open those files.
.q4nx6 GB · 100%
From the Hugging Face model README
FastFlowLM Q4NX conversion of tomg-group-umd/DynaGuard-8B-NPU2 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 | tomg-group-umd/DynaGuard-8B-NPU2 |
| Source GGUF | DynaGuard-8B.i1-Q4_1.gguf |
| Weights | model.q4nx (5.57 GB) |
| Modality | language |
| FLM version | 1.0.2 |
| Converted | 2026-08-18 |
This repository works with flm-add, a small installer that copies the model
into the FastFlowLM user directory and registers the tag. 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/DynaGuard-8B-NPU2 --family qwen3.5
FLM_CONFIG_PATH="$HOME/.config/flm/model_list.json" FLM_XCLBIN_PATH="$HOME/.config/flm" flm run dynaguard:8b
| File | Description |
|---|---|
model.q4nx | Quantized weights (Q8_0 / Q4_1 / BF16) |
config.json | FLM runtime configuration |
tokenizer.json | Tokenizer vocabulary |
tokenizer_config.json | Tokenizer configuration |
chat_template.jinja | Chat template |
See the original model card: tomg-group-umd/DynaGuard-8B-NPU2