Instructions to use prithivMLmods/FastThink-0.5B-Tiny-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use prithivMLmods/FastThink-0.5B-Tiny-GGUF with Transformers:

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

pipe = pipeline("text-generation", model="prithivMLmods/FastThink-0.5B-Tiny-GGUF")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("prithivMLmods/FastThink-0.5B-Tiny-GGUF", dtype="auto")

llama-cpp-python

How to use prithivMLmods/FastThink-0.5B-Tiny-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="prithivMLmods/FastThink-0.5B-Tiny-GGUF",
	filename="FastThink-0.5B-Tiny.BF16.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use prithivMLmods/FastThink-0.5B-Tiny-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf prithivMLmods/FastThink-0.5B-Tiny-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf prithivMLmods/FastThink-0.5B-Tiny-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 prithivMLmods/FastThink-0.5B-Tiny-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf prithivMLmods/FastThink-0.5B-Tiny-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 prithivMLmods/FastThink-0.5B-Tiny-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf prithivMLmods/FastThink-0.5B-Tiny-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 prithivMLmods/FastThink-0.5B-Tiny-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf prithivMLmods/FastThink-0.5B-Tiny-GGUF:Q4_K_M

Use Docker

docker model run hf.co/prithivMLmods/FastThink-0.5B-Tiny-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use prithivMLmods/FastThink-0.5B-Tiny-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "prithivMLmods/FastThink-0.5B-Tiny-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "prithivMLmods/FastThink-0.5B-Tiny-GGUF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/prithivMLmods/FastThink-0.5B-Tiny-GGUF:Q4_K_M

SGLang

How to use prithivMLmods/FastThink-0.5B-Tiny-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 "prithivMLmods/FastThink-0.5B-Tiny-GGUF" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "prithivMLmods/FastThink-0.5B-Tiny-GGUF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "prithivMLmods/FastThink-0.5B-Tiny-GGUF" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "prithivMLmods/FastThink-0.5B-Tiny-GGUF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Ollama
How to use prithivMLmods/FastThink-0.5B-Tiny-GGUF with Ollama:
```
ollama run hf.co/prithivMLmods/FastThink-0.5B-Tiny-GGUF:Q4_K_M
```

Unsloth Studio new

How to use prithivMLmods/FastThink-0.5B-Tiny-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 prithivMLmods/FastThink-0.5B-Tiny-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 prithivMLmods/FastThink-0.5B-Tiny-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for prithivMLmods/FastThink-0.5B-Tiny-GGUF to start chatting

Docker Model Runner
How to use prithivMLmods/FastThink-0.5B-Tiny-GGUF with Docker Model Runner:
```
docker model run hf.co/prithivMLmods/FastThink-0.5B-Tiny-GGUF:Q4_K_M
```

Lemonade

How to use prithivMLmods/FastThink-0.5B-Tiny-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull prithivMLmods/FastThink-0.5B-Tiny-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.FastThink-0.5B-Tiny-GGUF-Q4_K_M

List all available models

lemonade list

FastThink-0.5B-Tiny-GGUF

FastThink-0.5B-Tiny is a reasoning-focused model based on Qwen2.5. They have released a range of base language models and instruction-tuned language models, spanning from 0.5 billion to 72 billion parameters.

Model Files

File	Size	Description
README.md	31 Bytes	Project documentation
config.json	31 Bytes	Model configuration
.gitattributes	2.39 kB	Git attributes configuration
FastThink-0.5B-Tiny.BF16.gguf	994 MB	BFloat16 quantized model
FastThink-0.5B-Tiny.F16.gguf	994 MB	Float16 quantized model
FastThink-0.5B-Tiny.F32.gguf	1.98 GB	Float32 full precision model
FastThink-0.5B-Tiny.Q2_K.gguf	339 MB	2-bit K-quantized model
FastThink-0.5B-Tiny.Q3_K_L.gguf	369 MB	3-bit K-quantized model (Large)
FastThink-0.5B-Tiny.Q3_K_M.gguf	355 MB	3-bit K-quantized model (Medium)
FastThink-0.5B-Tiny.Q3_K_S.gguf	338 MB	3-bit K-quantized model (Small)
FastThink-0.5B-Tiny.Q4_K_M.gguf	398 MB	4-bit K-quantized model (Medium)
FastThink-0.5B-Tiny.Q4_K_S.gguf	385 MB	4-bit K-quantized model (Small)
FastThink-0.5B-Tiny.Q5_K_M.gguf	420 MB	5-bit K-quantized model (Medium)
FastThink-0.5B-Tiny.Q5_K_S.gguf	413 MB	5-bit K-quantized model (Small)
FastThink-0.5B-Tiny.Q6_K.gguf	506 MB	6-bit K-quantized model
FastThink-0.5B-Tiny.Q8_0.gguf	531 MB	8-bit quantized model

Quants Usage

(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)

Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better):

Downloads last month: 118

GGUF

Model size

0.5B params

Architecture

qwen2

Hardware compatibility

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

16-bit

32-bit

Model tree for prithivMLmods/FastThink-0.5B-Tiny-GGUF

Base model

Qwen/Qwen2.5-0.5B

Finetuned

Qwen/Qwen2.5-0.5B-Instruct

Quantized

prithivMLmods/FastThink-0.5B-Tiny

Quantized

(4)

this model