Instructions to use SEE7/AstheralPlus-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 SEE7/AstheralPlus-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 SEE7/AstheralPlus-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf SEE7/AstheralPlus-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 SEE7/AstheralPlus-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf SEE7/AstheralPlus-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 SEE7/AstheralPlus-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama cli -hf SEE7/AstheralPlus-GGUF:Q4_K_M

Use Docker

docker model run hf.co/SEE7/AstheralPlus-GGUF:Q4_K_M

Llama new
LM Studio
Jan
Ollama
How to use SEE7/AstheralPlus-GGUF with Ollama:
```
ollama run hf.co/SEE7/AstheralPlus-GGUF:Q4_K_M
```
Unsloth Desktop

How to use SEE7/AstheralPlus-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf SEE7/AstheralPlus-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": "SEE7/AstheralPlus-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use SEE7/AstheralPlus-GGUF with Docker Model Runner:
```
docker model run hf.co/SEE7/AstheralPlus-GGUF:Q4_K_M
```

Lemonade

How to use SEE7/AstheralPlus-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull SEE7/AstheralPlus-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.AstheralPlus-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use SEE7/AstheralPlus-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 SEE7/AstheralPlus-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 SEE7/AstheralPlus-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use SEE7/AstheralPlus-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf SEE7/AstheralPlus-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 "SEE7/AstheralPlus-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"

AstheralPlus GGUF

GGUF quantizations of SEE7/AstheralPlus, generated with llama.cpp 5676dfbe01e7ebe0387913680eee0ed39bf4a363.

Provided Quants

Measured decimal GB, sorted by file size. Each linked file has passed GGUF structure and upload hash checks.

Link	Type	Size/GB
GGUF	imatrix	0.056
GGUF	i1-IQ1_S	12.017
GGUF	i1-IQ1_M	12.017
GGUF	i1-IQ2_XXS	12.017
GGUF	i1-IQ2_XS	12.026
GGUF	i1-Q3_K_S	12.061
GGUF	i1-IQ2_S	12.066
GGUF	i1-IQ2_M	12.066
GGUF	i1-Q2_K	12.066
GGUF	i1-IQ3_XXS	12.066
GGUF	i1-IQ3_XS	12.066
GGUF	i1-IQ3_S	12.066
GGUF	i1-IQ4_XS	12.096
GGUF	i1-Q2_K_S	12.136
GGUF	i1-IQ3_M	12.203
GGUF	i1-Q3_K_M	12.916
GGUF	i1-Q3_K_L	13.335
GGUF	i1-Q4_K_M	15.805

Calibration

Importance data is collected from real forward passes over a deterministic multilingual and instruction sample of AstheralDataset. Corpus hash, chunk settings, exact tensor formats, and file SHA-256 hashes are recorded in manifest.json.

AstheralPlus begins with native MXFP4 expert weights. The converter preserves those weights before each requested quantization recipe runs. Tensor dimensions require mixed-format fallbacks in several recipes; the manifest records the actual tensor formats in every file.

Downloads last month: -

GGUF

Model size

21B params

Architecture

gpt-oss

Hardware compatibility

1-bit

2-bit

3-bit

4-bit

View +1 variant

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for SEE7/AstheralPlus-GGUF

Base model

openai/gpt-oss-20b

Finetuned

SEE7/AstheralPlus

Quantized

(1)

this model