Instructions to use Pinkstack/Superthoughts-lite-v2-MOE-Llama3.2-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Pinkstack/Superthoughts-lite-v2-MOE-Llama3.2-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Pinkstack/Superthoughts-lite-v2-MOE-Llama3.2-GGUF",
	filename="superthoughts-lite-v2-moe-llama3.2-0506.q4_k_m.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use Pinkstack/Superthoughts-lite-v2-MOE-Llama3.2-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Pinkstack/Superthoughts-lite-v2-MOE-Llama3.2-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf Pinkstack/Superthoughts-lite-v2-MOE-Llama3.2-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Pinkstack/Superthoughts-lite-v2-MOE-Llama3.2-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf Pinkstack/Superthoughts-lite-v2-MOE-Llama3.2-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/Superthoughts-lite-v2-MOE-Llama3.2-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Pinkstack/Superthoughts-lite-v2-MOE-Llama3.2-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/Superthoughts-lite-v2-MOE-Llama3.2-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Pinkstack/Superthoughts-lite-v2-MOE-Llama3.2-GGUF:Q4_K_M

Use Docker

docker model run hf.co/Pinkstack/Superthoughts-lite-v2-MOE-Llama3.2-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use Pinkstack/Superthoughts-lite-v2-MOE-Llama3.2-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Pinkstack/Superthoughts-lite-v2-MOE-Llama3.2-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/Superthoughts-lite-v2-MOE-Llama3.2-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Pinkstack/Superthoughts-lite-v2-MOE-Llama3.2-GGUF:Q4_K_M

Ollama
How to use Pinkstack/Superthoughts-lite-v2-MOE-Llama3.2-GGUF with Ollama:
```
ollama run hf.co/Pinkstack/Superthoughts-lite-v2-MOE-Llama3.2-GGUF:Q4_K_M
```

Unsloth Studio new

How to use Pinkstack/Superthoughts-lite-v2-MOE-Llama3.2-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/Superthoughts-lite-v2-MOE-Llama3.2-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/Superthoughts-lite-v2-MOE-Llama3.2-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/Superthoughts-lite-v2-MOE-Llama3.2-GGUF to start chatting

Pi new

How to use Pinkstack/Superthoughts-lite-v2-MOE-Llama3.2-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf Pinkstack/Superthoughts-lite-v2-MOE-Llama3.2-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/Superthoughts-lite-v2-MOE-Llama3.2-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use Pinkstack/Superthoughts-lite-v2-MOE-Llama3.2-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf Pinkstack/Superthoughts-lite-v2-MOE-Llama3.2-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/Superthoughts-lite-v2-MOE-Llama3.2-GGUF:Q4_K_M

Run Hermes

hermes

Docker Model Runner
How to use Pinkstack/Superthoughts-lite-v2-MOE-Llama3.2-GGUF with Docker Model Runner:
```
docker model run hf.co/Pinkstack/Superthoughts-lite-v2-MOE-Llama3.2-GGUF:Q4_K_M
```

Lemonade

How to use Pinkstack/Superthoughts-lite-v2-MOE-Llama3.2-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Pinkstack/Superthoughts-lite-v2-MOE-Llama3.2-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Superthoughts-lite-v2-MOE-Llama3.2-GGUF-Q4_K_M

List all available models

lemonade list

Gguf version. 3.91B parameters, 2 experts active, 4 in total.

[GGUF !! Full precision !! BF16]

INFORMATION

This is the non-experimental version of Superthoughts Lite v2. Offering better accuracy at all tasks, better performance and less looping while generating responses.

We trained it by first creating a base model for all the experts, which was fine-tuned using GRPO techniques using Unsloth on top of meta-llama/Llama-3.2-1B-Instruct. After making the base model, we trained each potential expert using SFT. After doing SFT, we did GRPO again. in total there are 4 experts:

Chat reasoning expert,
Math reasoning expert,
Code reasoning expert,
Science reasoning expert.

By doing this, we obtained a powerful, lite reasoning model that is very usable for its size.

This model is a direct replacement of Pinkstack/Superthoughts-lite-v1. Pinkstack/Superthoughts-lite-v1 was not able to generate code, and had very poor text performance. V2 is much more usable.

You should use this system prompt:

Thinking: enabled.

Follow this format strictly:
<think>
Write your step-by-step reasoning here.
Break down the problem into smaller parts.
Solve each part systematically.
Check your work and verify the answer makes sense.
</think>
[Your final answer after thinking].

Model information

The model can generate up to 16,380 tokens and has a context size of 131072 It has been fine tuned to generated thinking data in-between <think> xml tags. note that it may still have some slight looping but they are rare.

LIMITATIONS

While some safety alignment was done by us, it was very minimal. Thus, the model can be uncensored at times. In addition, users and providers alike should be aware that all large language models (LLM's), including this one can hallucinate and output false information. Always double check responses.

Chat model knows very well what it is, thus unless you provide it the proper information, it may make things up.

By using this model, you agree to the LLAMA 3.2 COMMUNITY LICENSE.

GGUF TEMPLATE

{{ if .Messages }}
{{- if or .System .Tools }}<|start_header_id|>system<|end_header_id|>
{{- if .System }}

{{ .System }}
{{- end }}
{{- if .Tools }}

You are a helpful assistant with tool calling capabilities. When you receive a tool call response, use the output to format an answer to the original use question.
{{- end }}
{{- end }}<|eot_id|>
{{- range $i, $_ := .Messages }}
{{- $last := eq (len (slice $.Messages $i)) 1 }}
{{- if eq .Role "user" }}<|start_header_id|>user<|end_header_id|>
{{- if and $.Tools $last }}

Given the following functions, please respond with a JSON for a function call with its proper arguments that best answers the given prompt.

Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}. Do not use variables.

{{ $.Tools }}
{{- end }}

{{ .Content }}<|eot_id|>{{ if $last }}<|start_header_id|>assistant<|end_header_id|>

{{ end }}
{{- else if eq .Role "assistant" }}<|start_header_id|>assistant<|end_header_id|>
{{- if .ToolCalls }}

{{- range .ToolCalls }}{"name": "{{ .Function.Name }}", "parameters": {{ .Function.Arguments }}}{{ end }}
{{- else }}

{{ .Content }}{{ if not $last }}<|eot_id|>{{ end }}
{{- end }}
{{- else if eq .Role "tool" }}<|start_header_id|>ipython<|end_header_id|>

{{ .Content }}<|eot_id|>{{ if $last }}<|start_header_id|>assistant<|end_header_id|>

{{ end }}
{{- end }}
{{- end }}
{{- else }}
{{- if .System }}<|start_header_id|>system<|end_header_id|>

{{ .System }}<|eot_id|>{{ end }}{{ if .Prompt }}<|start_header_id|>user<|end_header_id|>

{{ .Prompt }}<|eot_id|>{{ end }}<|start_header_id|>assistant<|end_header_id|>

{{ end }}{{ .Response }}{{ if .Response }}<|eot_id|>{{ end }}