Downloads · 30 days
30
21% of all-time downloads
Gemma4-E2B-Claude-Sonnet-Distilled-NPU2
Atomic-Germ/Gemma4-E2B-Claude-Sonnet-Distilled-NPU2
Gemma4-E2B-Claude-Sonnet-Distilled-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 transformers. The card lists the license as apache-2.0.
FastFlowLM Q4NX conversion of Lufel6848/Gemma4-E2B-Claude-Sonnet-Distilled for AMD XDNA NPU inference.
All-time downloads
146
Public
Repo size
6 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.q4nx6 GB · 99%
At a glance
- Task
- Image-Text-to-Text
- Library
- transformers
- License
- apache-2.0
- Model type
- gemma4_text
- Access
- Public
- Created
- Aug 23, 2026
- Updated
- Sep 17, 2026
- SHA
- a6098bfa
Try a prompt
Base models
Model card
From the Hugging Face model README
Gemma4-E2B-Claude-Sonnet-Distilled-NPU2
FastFlowLM Q4NX conversion of Lufel6848/Gemma4-E2B-Claude-Sonnet-Distilled 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 | Lufel6848/Gemma4-E2B-Claude-Sonnet-Distilled |
| Source GGUF | gemma-4-e2b-it.Q8_0.gguf |
| Weights | model.q4nx (4.35 GB) |
| Modality | language / vision / audio |
| FLM version | 1.0.1 |
| Converted | 2026-08-23 |
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. 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/Gemma4-E2B-Claude-Sonnet-Distilled-NPU2 --family qwen3.5 --xclbin-from Gemma4-E2B-Claude-Sonnet-Distilled-NPU2
FLM_CONFIG_PATH="$HOME/.config/flm/model_list.json" FLM_XCLBIN_PATH="$HOME/.config/flm" flm run Gemma4-E2B-Claude-Sonnet-Distilled-NPU2
Files
| File | Description |
|---|---|
model.q4nx | Quantized weights (Q8_0 / Q4_1 / BF16) |
audio_weight.q4nx | Audio encoder weights |
config.json | FLM runtime configuration |
tokenizer.json | Tokenizer vocabulary |
tokenizer_config.json | Tokenizer configuration |
chat_template.jinja | Chat template |
vision_weight.q4nx | Vision model |
Source model card
See the original model card: Lufel6848/Gemma4-E2B-Claude-Sonnet-Distilled
- Task
- Image-Text-to-Text
- Library
- transformers
- Type
- gemma4_text
- License
- apache-2.0
- Languages
- en
- Created
- Aug 23, 2026
- Updated
- Sep 17, 2026