Instructions to use Abiray/Agents-A1-Q4_K_M-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use Abiray/Agents-A1-Q4_K_M-GGUF with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Abiray/Agents-A1-Q4_K_M-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Abiray/Agents-A1-Q4_K_M-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Abiray/Agents-A1-Q4_K_M-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Abiray/Agents-A1-Q4_K_M-GGUF:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf Abiray/Agents-A1-Q4_K_M-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Abiray/Agents-A1-Q4_K_M-GGUF:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf Abiray/Agents-A1-Q4_K_M-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Abiray/Agents-A1-Q4_K_M-GGUF:Q4_K_M

Use Docker

docker model run hf.co/Abiray/Agents-A1-Q4_K_M-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use Abiray/Agents-A1-Q4_K_M-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Abiray/Agents-A1-Q4_K_M-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Abiray/Agents-A1-Q4_K_M-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Abiray/Agents-A1-Q4_K_M-GGUF:Q4_K_M

Ollama
How to use Abiray/Agents-A1-Q4_K_M-GGUF with Ollama:
```
ollama run hf.co/Abiray/Agents-A1-Q4_K_M-GGUF:Q4_K_M
```
Unsloth Desktop

How to use Abiray/Agents-A1-Q4_K_M-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Abiray/Agents-A1-Q4_K_M-GGUF:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "Abiray/Agents-A1-Q4_K_M-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use Abiray/Agents-A1-Q4_K_M-GGUF with Docker Model Runner:
```
docker model run hf.co/Abiray/Agents-A1-Q4_K_M-GGUF:Q4_K_M
```

Lemonade

How to use Abiray/Agents-A1-Q4_K_M-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Abiray/Agents-A1-Q4_K_M-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Agents-A1-Q4_K_M-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use Abiray/Agents-A1-Q4_K_M-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Abiray/Agents-A1-Q4_K_M-GGUF:Q4_K_M

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default Abiray/Agents-A1-Q4_K_M-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use Abiray/Agents-A1-Q4_K_M-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Abiray/Agents-A1-Q4_K_M-GGUF:Q4_K_M

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "Abiray/Agents-A1-Q4_K_M-GGUF:Q4_K_M" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

Agents-A1-Q4_K_M-GGUF

This repository contains the GGUF quantized version of Agents-A1, a 35B Mixture-of-Experts (MoE) agentic model developed by InternScience. Quantization has been performed using the Q4_K_M method to optimize performance and reduce memory consumption while preserving agentic reasoning capabilities.

Original Model: InternScience/Agents-A1
Technical Report: arXiv:2606.30616

Provided Files

File Name	Size	Quantization Method	Description
`Agents-A1-Q4_K_M.gguf`	21.2 GB	Q4_K_M	Medium 4-bit quantization. Recommended balance between size, speed, and accuracy.

About Agents-A1

Agents‑A1 is a 35B Mixture‑of‑Experts agentic model built to scale heterogeneous agentic abilities across multiple domains including Long‑horizon Search, Engineering, Scientific Research, Instruction Following, and Tool-calling.

Key Highlights

Agentic Reasoning: Excels at decomposing complex tasks into executable sub-steps, planning ahead, and adapting its strategy based on intermediate results.
Tool Use: Natively supports function calling and tool integration, enabling seamless interaction with APIs, code interpreters, search engines, and external tools.
Scientific and Professional Reasoning: Handles tool-integrated scientific reasoning and professional knowledge question answering.
Instruction Following: Precisely follows detailed, multi-constraint instructions across diverse domains.

Performance Overview

Despite operating in the ~35B model class, Agents-A1 delivers highly competitive performance against frontier-scale systems such as GPT-5.5, DeepSeek-V4-pro, and Kimi-K2.6. It achieves overall SOTA results on several challenging benchmarks, including Seal-0 (56.4), HiPhO (46.4), FrontierScience-Olympiad (79.0), FrontierScience-Research (40.0), IFBench (80.6), and IFEval (94.8).

Deployment & Usage

You can run this GGUF model using popular inference engines like llama.cpp or Ollama.

Option 1: Using llama.cpp

To run inference via the command line with llama.cpp, download the file and use the following command structure:

./llama-cli \
  --model Agents-A1-Q4_K_M.gguf \
  --prompt "<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n<|im_start|>user\nHello, who are you?<|im_end|>\n<|im_start|>assistant\n" \
  --ctx-size 8192 \
  --threads 8

Downloads last month: 38

GGUF

Model size

35B params

Architecture

qwen35moe

Hardware compatibility

4-bit

Model tree for Abiray/Agents-A1-Q4_K_M-GGUF

Base model

InternScience/Agents-A1

Quantized

(74)

this model

Paper for Abiray/Agents-A1-Q4_K_M-GGUF

Scaling the Horizon, Not the Parameters: Reaching Trillion-Parameter Performance with a 35B Agent

Paper • 2606.30616 • Published Jun 29 • 105