Instructions to use Parakon/Parakon-30B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use Parakon/Parakon-30B 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 Parakon/Parakon-30B
# Run inference directly in the terminal:
llama cli -hf Parakon/Parakon-30B

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Parakon/Parakon-30B
# Run inference directly in the terminal:
llama cli -hf Parakon/Parakon-30B

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 Parakon/Parakon-30B
# Run inference directly in the terminal:
./llama-cli -hf Parakon/Parakon-30B

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 Parakon/Parakon-30B
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Parakon/Parakon-30B

Use Docker

docker model run hf.co/Parakon/Parakon-30B

LM Studio
Jan

vLLM

How to use Parakon/Parakon-30B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Parakon/Parakon-30B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Parakon/Parakon-30B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Parakon/Parakon-30B

Ollama
How to use Parakon/Parakon-30B with Ollama:
```
ollama run hf.co/Parakon/Parakon-30B
```
Unsloth Desktop

How to use Parakon/Parakon-30B with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Parakon/Parakon-30B

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": "Parakon/Parakon-30B"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use Parakon/Parakon-30B with Docker Model Runner:
```
docker model run hf.co/Parakon/Parakon-30B
```

Lemonade

How to use Parakon/Parakon-30B with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Parakon/Parakon-30B

Run and chat with the model

lemonade run user.Parakon-30B-{{QUANT_TAG}}

List all available models

lemonade list

Hermes Agent

How to use Parakon/Parakon-30B with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Parakon/Parakon-30B

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 Parakon/Parakon-30B

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use Parakon/Parakon-30B with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Parakon/Parakon-30B

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 "Parakon/Parakon-30B" \
  --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"

Parakon 30B

Qwen3-30B-A3B-Instruct-2507 compressed by Parakon's pipeline: 61 GB (fp16) → 5.94 GB, a 10.3× reduction, with 88% median quality retention on a six-benchmark suite.

Quality — paired, same harness

Each figure is the compressed model's score as a share of the same checkpoint at full precision, run through the same harness (greedy decoding, one configuration). Retention holds on knowledge, tool use and reasoning; it thins on code and strict instruction formatting — reported at the same size as the rest.

Benchmark	Retention
MuSR (reasoning)	93%
GSM8K (math)	90%
MMLU-Redux (knowledge)	88%
BFCL-v3 (tool calling)	88%
HumanEval+ (code)	77%
IFEval, prompt-strict (instruction following)	76%
Median	88%

Speed — measured

Hardware	Throughput
M3 MacBook Air, 16 GB (Metal)	12.7 tokens/s
CPU only, 48 vCPU	7.7 tokens/s

Recommended settings

Chat template: Qwen3 (ChatML). Native context length: up to 262,144 tokens.

General-purpose sampling:

Parameter	Value
temperature	0.7
top_p	0.8
top_k	20
min_p	0

Runtime

This artifact uses Parakon's own storage format and requires the Parakon runtime (custom GPU, Metal and CPU kernels) to execute. The runtime is provided to evaluation partners together with reproduction instructions for every number above.

License & access

Released under the Parakon Community License:

Always free — research, personal use, evaluation, and benchmarking (publishing your results is encouraged, never restricted)
Free commercial use for organizations under 100 employees and $1M annual revenue — production included
Larger organizations need a commercial agreement — contact the Parakon team through this organization's page
No re-hosting — refer others to this repository for the weights

The runtime is licensed separately. For deployment licensing, runtime access, or compression engagements on your own models: get in touch.

Downloads last month: 5

GGUF

Model size

31B params

Architecture

qwen3moe

Hardware compatibility

We're not able to determine the quantization variants.

View all variants

Model tree for Parakon/Parakon-30B

Base model

Qwen/Qwen3-30B-A3B-Instruct-2507

Quantized

(135)

this model