Instructions to use sriram1983007/SRA-RiskGate-4B-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 sriram1983007/SRA-RiskGate-4B-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 sriram1983007/SRA-RiskGate-4B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf sriram1983007/SRA-RiskGate-4B-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 sriram1983007/SRA-RiskGate-4B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf sriram1983007/SRA-RiskGate-4B-GGUF:Q4_K_M

Build from source code

git clone https://github.com/ggml-org/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-app
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama serve -hf sriram1983007/SRA-RiskGate-4B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama cli -hf sriram1983007/SRA-RiskGate-4B-GGUF:Q4_K_M

Use Docker

docker model run hf.co/sriram1983007/SRA-RiskGate-4B-GGUF:Q4_K_M

Llama new
LM Studio
Jan

vLLM

How to use sriram1983007/SRA-RiskGate-4B-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "sriram1983007/SRA-RiskGate-4B-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": "sriram1983007/SRA-RiskGate-4B-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/sriram1983007/SRA-RiskGate-4B-GGUF:Q4_K_M

Ollama
How to use sriram1983007/SRA-RiskGate-4B-GGUF with Ollama:
```
ollama run hf.co/sriram1983007/SRA-RiskGate-4B-GGUF:Q4_K_M
```
Unsloth Desktop

How to use sriram1983007/SRA-RiskGate-4B-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf sriram1983007/SRA-RiskGate-4B-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": "sriram1983007/SRA-RiskGate-4B-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use sriram1983007/SRA-RiskGate-4B-GGUF with Docker Model Runner:
```
docker model run hf.co/sriram1983007/SRA-RiskGate-4B-GGUF:Q4_K_M
```

Lemonade

How to use sriram1983007/SRA-RiskGate-4B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull sriram1983007/SRA-RiskGate-4B-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.SRA-RiskGate-4B-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use sriram1983007/SRA-RiskGate-4B-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 sriram1983007/SRA-RiskGate-4B-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 sriram1983007/SRA-RiskGate-4B-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use sriram1983007/SRA-RiskGate-4B-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf sriram1983007/SRA-RiskGate-4B-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 "sriram1983007/SRA-RiskGate-4B-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"

SRA-RiskGate-4B (GGUF)

GGUF builds of SRA-RiskGate-4B, a 4B model that checks a stablecoin payment before an AI agent sends it and answers approve, hold or reject. For llama.cpp, LM Studio, Ollama and similar.

📄 Paper: preprint on Zenodo · full write-up on Ready Tensor · discuss on alphaXiv

File	Size	Notes
`SRA-RiskGate-4B-Q8_0.gguf`	4.3 GB	Closest to full precision
`SRA-RiskGate-4B-Q6_K.gguf`	3.3 GB
`SRA-RiskGate-4B-Q5_K_M.gguf`	2.9 GB
`SRA-RiskGate-4B-Q4_K_M.gguf`	2.5 GB	Smallest recommended for gating real payments; the build behind the Ollama model

The benchmark results on the main model card were measured on the full-precision model. These quantized builds have not been benchmarked separately. Dispute adjudication is the most likely to degrade, so prefer Q8_0 or the full model for disputes.

Run it

Ollama (payment risk-gate system prompt, temperature 0 and an 8K context built in):

ollama run sriram1983007/sra-riskgate

llama.cpp:

llama-server -hf sriram1983007/SRA-RiskGate-4B-GGUF:Q4_K_M -c 8192 --temp 0

LM Studio: search for SRA-RiskGate-4B-GGUF, pick a file, and set temperature to 0.

Use the exact training prompt format from the main model card: the system prompt, then Evaluate this stablecoin payment. with the <context>, <payload> and <tool_results> blocks. Treat any answer that isn't a valid verdict as a hold.

More quantization sizes, including imatrix builds, are available from mradermacher: static and imatrix, and from tinyopsec: SRA-RiskGate-4B-GGUF (Q2_K to F16; builds below Q4 have not been evaluated).

📄 Citation

@misc{ramakrishnan2026srariskgate,
  author    = {Sriram Ramakrishnan},
  title     = {SRA-RiskGate: A Benchmark and a 4B Model for Gating Stablecoin Payments Made by AI Agents, and the Checks the Model Still Needs},
  year      = {2026},
  publisher = {Zenodo},
  doi       = {10.5281/zenodo.23715017},
  url       = {https://doi.org/10.5281/zenodo.23715017}
}

Full write-up: Ready Tensor.

License

Apache 2.0

Downloads last month: 794

GGUF

Model size

4B params

Architecture

qwen3

Hardware compatibility

4-bit

5-bit

6-bit

8-bit

Model tree for sriram1983007/SRA-RiskGate-4B-GGUF

Base model

Qwen/Qwen3-4B-Instruct-2507

Finetuned

sriram1983007/SRA-RiskGate-4B

Quantized

(5)

this model

Dataset used to train sriram1983007/SRA-RiskGate-4B-GGUF

Collection including sriram1983007/SRA-RiskGate-4B-GGUF

SRA-RiskGate: stablecoin payment risk & dispute models

Collection

A lightweight (4B) risk gate for stablecoin and AI-agent payments. Deterministic JSON verdicts, with fully reproducible benchmark results. • 7 items • Updated 17 days ago