Instructions to use Pinkstack/PARM-V2-QwQ-Qwen-2.5-o1-3B-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Pinkstack/PARM-V2-QwQ-Qwen-2.5-o1-3B-GGUF with Transformers:

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

pipe = pipeline("text-generation", model="Pinkstack/PARM-V2-QwQ-Qwen-2.5-o1-3B-GGUF")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("Pinkstack/PARM-V2-QwQ-Qwen-2.5-o1-3B-GGUF", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use Pinkstack/PARM-V2-QwQ-Qwen-2.5-o1-3B-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 Pinkstack/PARM-V2-QwQ-Qwen-2.5-o1-3B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Pinkstack/PARM-V2-QwQ-Qwen-2.5-o1-3B-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 Pinkstack/PARM-V2-QwQ-Qwen-2.5-o1-3B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Pinkstack/PARM-V2-QwQ-Qwen-2.5-o1-3B-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 Pinkstack/PARM-V2-QwQ-Qwen-2.5-o1-3B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Pinkstack/PARM-V2-QwQ-Qwen-2.5-o1-3B-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 Pinkstack/PARM-V2-QwQ-Qwen-2.5-o1-3B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Pinkstack/PARM-V2-QwQ-Qwen-2.5-o1-3B-GGUF:Q4_K_M

Use Docker

docker model run hf.co/Pinkstack/PARM-V2-QwQ-Qwen-2.5-o1-3B-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use Pinkstack/PARM-V2-QwQ-Qwen-2.5-o1-3B-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Pinkstack/PARM-V2-QwQ-Qwen-2.5-o1-3B-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": "Pinkstack/PARM-V2-QwQ-Qwen-2.5-o1-3B-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Pinkstack/PARM-V2-QwQ-Qwen-2.5-o1-3B-GGUF:Q4_K_M

SGLang

How to use Pinkstack/PARM-V2-QwQ-Qwen-2.5-o1-3B-GGUF 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 "Pinkstack/PARM-V2-QwQ-Qwen-2.5-o1-3B-GGUF" \
    --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": "Pinkstack/PARM-V2-QwQ-Qwen-2.5-o1-3B-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "Pinkstack/PARM-V2-QwQ-Qwen-2.5-o1-3B-GGUF" \
        --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": "Pinkstack/PARM-V2-QwQ-Qwen-2.5-o1-3B-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use Pinkstack/PARM-V2-QwQ-Qwen-2.5-o1-3B-GGUF with Ollama:
```
ollama run hf.co/Pinkstack/PARM-V2-QwQ-Qwen-2.5-o1-3B-GGUF:Q4_K_M
```

Unsloth Studio

How to use Pinkstack/PARM-V2-QwQ-Qwen-2.5-o1-3B-GGUF with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for Pinkstack/PARM-V2-QwQ-Qwen-2.5-o1-3B-GGUF to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for Pinkstack/PARM-V2-QwQ-Qwen-2.5-o1-3B-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Pinkstack/PARM-V2-QwQ-Qwen-2.5-o1-3B-GGUF to start chatting

How to use Pinkstack/PARM-V2-QwQ-Qwen-2.5-o1-3B-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Pinkstack/PARM-V2-QwQ-Qwen-2.5-o1-3B-GGUF:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "Pinkstack/PARM-V2-QwQ-Qwen-2.5-o1-3B-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use Pinkstack/PARM-V2-QwQ-Qwen-2.5-o1-3B-GGUF with Docker Model Runner:
```
docker model run hf.co/Pinkstack/PARM-V2-QwQ-Qwen-2.5-o1-3B-GGUF:Q4_K_M
```

Lemonade

How to use Pinkstack/PARM-V2-QwQ-Qwen-2.5-o1-3B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Pinkstack/PARM-V2-QwQ-Qwen-2.5-o1-3B-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.PARM-V2-QwQ-Qwen-2.5-o1-3B-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use Pinkstack/PARM-V2-QwQ-Qwen-2.5-o1-3B-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 Pinkstack/PARM-V2-QwQ-Qwen-2.5-o1-3B-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 Pinkstack/PARM-V2-QwQ-Qwen-2.5-o1-3B-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use Pinkstack/PARM-V2-QwQ-Qwen-2.5-o1-3B-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Pinkstack/PARM-V2-QwQ-Qwen-2.5-o1-3B-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 "Pinkstack/PARM-V2-QwQ-Qwen-2.5-o1-3B-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"

Want an upgrade / got a powerful device? Use https://huggingface.co/Pinkstack/SuperThoughts-CoT-14B-16k-o1-QwQ-GGUF/tree/main instead!

We are proud to announce, our new high quality model series - PARM2, Very high quality reasoning, math and coding abilities for a small size, that anyone can run on their device for free.

🧀 Which quant is right for you?

Q4: This model should be used on edge devices like high end phones or laptops due to its very compact size, quality is okay but fully usable.
Q8: This model should be used on most high end modern devices like rtx 3080, Responses are very high quality, but its slightly slower than Q4. (Runs at 9.89 tokens per second on a Samsung z fold 5 smartphone.) other formats were not included as Q4,Q8 have the best performance, quality.

This Parm v2 is based on Qwen 2.5 3B which has gotten many extra reasoning training parameters so it would have similar outputs to qwen QwQ / O.1 mini (only much, smaller.). We've trained it using the datasets here if you benchmarked this model let me know

This is a pretty lite model which can be run on high end phones pretty quickly using the q4 quant.

Passes "strawberry" test! (Q8 w/ msty & rtx 3080 10gb) ✅

To use this model, you must use a service which supports the GGUF file format. Additionaly, this is the Prompt Template options: efficient & accurate, answers stawberry text correctly ~90% of the time.

{{ if .System }}<|system|>
{{ .System }}<|im_end|>
{{ end }}{{ if .Prompt }}<|user|>
{{ .Prompt }}<|im_end|>
{{ end }}<|assistant|>
{{ .Response }}<|im_end|>

Or if you are using an anti prompt: <|im_end|>

Highly recommended to use with a system prompt. eg; You are a helpful assistant named Parm2 by Pinkstack. think step-by-step for complex stuff, use COT if neeed.