Instructions to use Pinkstack/SuperThoughts-CoT-14B-16k-o1-QwQ-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Pinkstack/SuperThoughts-CoT-14B-16k-o1-QwQ-GGUF with Transformers:

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

pipe = pipeline("text-generation", model="Pinkstack/SuperThoughts-CoT-14B-16k-o1-QwQ-GGUF")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("Pinkstack/SuperThoughts-CoT-14B-16k-o1-QwQ-GGUF", dtype="auto")

llama-cpp-python

How to use Pinkstack/SuperThoughts-CoT-14B-16k-o1-QwQ-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Pinkstack/SuperThoughts-CoT-14B-16k-o1-QwQ-GGUF",
	filename="Parm-phi-4.Q3_K_L.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-CoT-14B-16k-o1-QwQ-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-CoT-14B-16k-o1-QwQ-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf Pinkstack/SuperThoughts-CoT-14B-16k-o1-QwQ-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-CoT-14B-16k-o1-QwQ-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf Pinkstack/SuperThoughts-CoT-14B-16k-o1-QwQ-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-CoT-14B-16k-o1-QwQ-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Pinkstack/SuperThoughts-CoT-14B-16k-o1-QwQ-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-CoT-14B-16k-o1-QwQ-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Pinkstack/SuperThoughts-CoT-14B-16k-o1-QwQ-GGUF:Q4_K_M

Use Docker

docker model run hf.co/Pinkstack/SuperThoughts-CoT-14B-16k-o1-QwQ-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use Pinkstack/SuperThoughts-CoT-14B-16k-o1-QwQ-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Pinkstack/SuperThoughts-CoT-14B-16k-o1-QwQ-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-CoT-14B-16k-o1-QwQ-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Pinkstack/SuperThoughts-CoT-14B-16k-o1-QwQ-GGUF:Q4_K_M

SGLang

How to use Pinkstack/SuperThoughts-CoT-14B-16k-o1-QwQ-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/SuperThoughts-CoT-14B-16k-o1-QwQ-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/SuperThoughts-CoT-14B-16k-o1-QwQ-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/SuperThoughts-CoT-14B-16k-o1-QwQ-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/SuperThoughts-CoT-14B-16k-o1-QwQ-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use Pinkstack/SuperThoughts-CoT-14B-16k-o1-QwQ-GGUF with Ollama:
```
ollama run hf.co/Pinkstack/SuperThoughts-CoT-14B-16k-o1-QwQ-GGUF:Q4_K_M
```

Unsloth Studio new

How to use Pinkstack/SuperThoughts-CoT-14B-16k-o1-QwQ-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-CoT-14B-16k-o1-QwQ-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-CoT-14B-16k-o1-QwQ-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-CoT-14B-16k-o1-QwQ-GGUF to start chatting

Docker Model Runner
How to use Pinkstack/SuperThoughts-CoT-14B-16k-o1-QwQ-GGUF with Docker Model Runner:
```
docker model run hf.co/Pinkstack/SuperThoughts-CoT-14B-16k-o1-QwQ-GGUF:Q4_K_M
```

Lemonade

How to use Pinkstack/SuperThoughts-CoT-14B-16k-o1-QwQ-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Pinkstack/SuperThoughts-CoT-14B-16k-o1-QwQ-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.SuperThoughts-CoT-14B-16k-o1-QwQ-GGUF-Q4_K_M

List all available models

lemonade list

safetensors version: Pinkstack/SuperThoughts-CoT-14B-16k-o1-QwQ Phi-4 Technical Report (SuperThoughts 14B is based on phi-4)

You must use this prompt format: https://huggingface.co/Pinkstack/SuperThoughts-CoT-14B-16k-o1-QwQ-GGUF#format

We are very proud to announce, SuperThoughts, but you can just call it o1 mini 😉

A reasoning ai model based on Phi-4, which is better that QwQ at everything but Ifeval, but at a smaller size, really good at math and answers step by step in multiple languages with any prompt as reasoning is built into the prompt format.

Please check the examples we provided: https://huggingface.co/Pinkstack/SuperThoughts-CoT-14B-16k-o1-QwQ-GGUF#%F0%9F%A7%80-examples Beats qwen/qwq at MATH & MuSR & GPQA (MuSR being a reasoning benchmark) Evaluation:

Unlike previous models we've uploaded, this one is the best one we've published! Answers in two steps: Reasoning -> Final answer like o1 mini and other similar reasoning ai models.

🧀 Which quant is right for you? (all tested!)

Q3: This quant should be used on most high-end devices like rtx 2080TI's, Responses are very high quality, but its slightly slower than Q4. (Runs at ~1 tokens per second or less on a Samsung z fold 5 smartphone.)
Q4: This quant should be used on high-end modern devices like rtx 3080's or any GPU,TPU,CPU that is powerful enough and has at minimum 15gb of available memory, (On servers and high-end computers we personally use it.) reccomened.
Q8: This quant should be used on very high-end modern devices which can handle it's power, it is very powerful but q4 is more well rounded, not recommended.

Evaluation Results

Detailed results can be found here! Summarized results can be found here! Please note, the low IFEVAL results is probably due to it always reasoning, it does have issues with instruction following.

Metric	Value (%)
Average	31.17
IFEval (0-Shot)	5.15
BBH (3-Shot)	52.85
MATH Lvl 5 (4-Shot)	40.79
GPQA (0-shot)	19.02
MuSR (0-shot)	21.79
MMLU-PRO (5-shot)	47.43

Format

the model uses this prompt format: (modified phi-4 prompt)

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

It is recommended to use a system prompt like this one:

You are a helpful ai assistant. Make sure to put your finalanswer at the end.

🧀 Examples:

(q4_k_m, 10GB rtx 3080, 64GB memory, running inside of MSTY, all use "You are a friendly ai assistant." as the System prompt.) example 1: example 2: example 3: example 4:

All generated locally and pretty quickly too!

🧀 Information

⚠️ A low temperature must be used to ensure it won't fail at reasoning. we use 0.3 - 0.8!
⚠️ Due to the current prompt format, it may sometimes put <|FinalAnswer|> without providing a final answer at the end, you can ignore this or modify the prompt format.
this is out flagship model, with top-tier reasoning, rivaling gemini-flash-exp-2.0-thinking and o1 mini. results are overall similar to both of them, and it even beats QwQ at certain benchmarks.

Supported languages: Arabic, Chinese, Czech, Danish, Dutch, English, Finnish, French, German, Hebrew, Hungarian, Italian, Japanese, Korean, Norwegian, Polish, Portuguese, Russian, Spanish, Swedish, Thai, Turkish, Ukrainian

🧀 Uploaded model

Developed by: Pinkstack
License: MIT
Finetuned from model : Pinkstack/PARM-V1-phi-4-4k-CoT-pytorch

This Phi-4 model was trained with Unsloth and Huggingface's TRL library.

Downloads last month: 145

GGUF

Model size

15B params

Architecture

llama

Hardware compatibility

3-bit

4-bit

8-bit

Model tree for Pinkstack/SuperThoughts-CoT-14B-16k-o1-QwQ-GGUF

Base model

microsoft/phi-4

Finetuned

Pinkstack/Parm-2-CoT-14B-16k-o1-QwQ

Quantized

(7)

this model

Paper for Pinkstack/SuperThoughts-CoT-14B-16k-o1-QwQ-GGUF

Phi-4 Technical Report

Paper • 2412.08905 • Published Dec 12, 2024 • 123

Evaluation results

averaged accuracy on IFEval (0-Shot)
Open LLM Leaderboard

5.150
normalized accuracy on BBH (3-Shot)
test set Open LLM Leaderboard

52.850
exact match on MATH Lvl 5 (4-Shot)
test set Open LLM Leaderboard

40.790
acc_norm on GPQA (0-shot)
Open LLM Leaderboard

19.020
acc_norm on MuSR (0-shot)
Open LLM Leaderboard

21.790
accuracy on MMLU-PRO (5-shot)
test set Open LLM Leaderboard

47.430