Instructions to use APMIC/ACE-3-F-26B-A4B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use APMIC/ACE-3-F-26B-A4B with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("image-text-to-text", model="APMIC/ACE-3-F-26B-A4B")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("APMIC/ACE-3-F-26B-A4B")
model = AutoModelForMultimodalLM.from_pretrained("APMIC/ACE-3-F-26B-A4B", device_map="auto")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=256)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use APMIC/ACE-3-F-26B-A4B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "APMIC/ACE-3-F-26B-A4B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "APMIC/ACE-3-F-26B-A4B",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/APMIC/ACE-3-F-26B-A4B

SGLang

How to use APMIC/ACE-3-F-26B-A4B with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "APMIC/ACE-3-F-26B-A4B" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "APMIC/ACE-3-F-26B-A4B",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "APMIC/ACE-3-F-26B-A4B" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "APMIC/ACE-3-F-26B-A4B",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use APMIC/ACE-3-F-26B-A4B with Docker Model Runner:
```
docker model run hf.co/APMIC/ACE-3-F-26B-A4B
```

You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

ACE-3-F-26B-A4B-260804

Model Description

ACE-3-F-26B-A4B-260804 is an enterprise-grade, production-ready large language model developed and optimized by APMIC for financial and regulated-business scenarios.

The model is based on google/gemma-4-26B-A4B-it and has been further optimized through quantization and financial-domain adaptation to support high-reliability deployment in Traditional Chinese business environments.

This release demonstrates APMIC’s end-to-end capability in:

Enterprise LLM optimization and deployment engineering
Quantization-aware inference optimization (A4B)
Financial language and Taiwan market localization
Deployment readiness for private cloud and on-premise AI infrastructures

Model Details

Developed by: APMIC
Model type: Gemma4ForConditionalGeneration (Transformers)
Language(s) (NLP): Traditional Chinese & English
License: gemma (Google usage license; gated on Hugging Face)

Key Capabilities

Financial Domain Strength

This model is specifically strengthened for finance-oriented prompts and terminology, with stronger alignment for:

Financial regulation and compliance interpretation
Financial customer service and communication workflows
Internal operations, account, and policy document support
Risk-sensitive wording consistency in Taiwan-specific business context

Robustness for Production Workflows

The model is suitable as a production support model for high-volume operations and is designed to operate with enterprise control layers for higher-risk use cases.

Hardware Optimization

Optimized for Modern GPU Deployment

ACE-3-F-26B-A4B-260804 is designed for efficient inference on modern GPU platforms through A4B-based optimization and inference-focused tuning.

This enables:

Lower memory footprint and inference latency
Better throughput stability under concurrent workloads
Practical private deployment with predictable cost and performance profiles

Positioning

This model demonstrates APMIC’s ability to transform open foundation models into financially-focused, localized, and deployment-ready AI assets.

It is intended for organizations requiring:

High-quality Traditional Chinese understanding for finance scenarios
Stable inference at scale in production settings
Regulated and enterprise-grade deployment control

Downloads last month: -

Safetensors

Model size

26B params

Tensor type

BF16

Model tree for APMIC/ACE-3-F-26B-A4B

Base model

google/gemma-4-26B-A4B

Finetuned

google/gemma-4-26B-A4B-it

Finetuned

(193)

this model