Instructions to use prithivMLmods/Olmo-3-Think-AIO-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use prithivMLmods/Olmo-3-Think-AIO-GGUF with Transformers:

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

pipe = pipeline("text-generation", model="prithivMLmods/Olmo-3-Think-AIO-GGUF")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("prithivMLmods/Olmo-3-Think-AIO-GGUF", dtype="auto")

llama-cpp-python

How to use prithivMLmods/Olmo-3-Think-AIO-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="prithivMLmods/Olmo-3-Think-AIO-GGUF",
	filename="Olmo-3-32B-Think.BF16.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use prithivMLmods/Olmo-3-Think-AIO-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/Olmo-3-Think-AIO-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf prithivMLmods/Olmo-3-Think-AIO-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/Olmo-3-Think-AIO-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf prithivMLmods/Olmo-3-Think-AIO-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/Olmo-3-Think-AIO-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf prithivMLmods/Olmo-3-Think-AIO-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/Olmo-3-Think-AIO-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf prithivMLmods/Olmo-3-Think-AIO-GGUF:Q4_K_M

Use Docker

docker model run hf.co/prithivMLmods/Olmo-3-Think-AIO-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use prithivMLmods/Olmo-3-Think-AIO-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "prithivMLmods/Olmo-3-Think-AIO-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": "prithivMLmods/Olmo-3-Think-AIO-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/prithivMLmods/Olmo-3-Think-AIO-GGUF:Q4_K_M

SGLang

How to use prithivMLmods/Olmo-3-Think-AIO-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/Olmo-3-Think-AIO-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": "prithivMLmods/Olmo-3-Think-AIO-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 "prithivMLmods/Olmo-3-Think-AIO-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": "prithivMLmods/Olmo-3-Think-AIO-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use prithivMLmods/Olmo-3-Think-AIO-GGUF with Ollama:
```
ollama run hf.co/prithivMLmods/Olmo-3-Think-AIO-GGUF:Q4_K_M
```

Unsloth Studio

How to use prithivMLmods/Olmo-3-Think-AIO-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/Olmo-3-Think-AIO-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/Olmo-3-Think-AIO-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/Olmo-3-Think-AIO-GGUF to start chatting

Docker Model Runner
How to use prithivMLmods/Olmo-3-Think-AIO-GGUF with Docker Model Runner:
```
docker model run hf.co/prithivMLmods/Olmo-3-Think-AIO-GGUF:Q4_K_M
```

Lemonade

How to use prithivMLmods/Olmo-3-Think-AIO-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull prithivMLmods/Olmo-3-Think-AIO-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Olmo-3-Think-AIO-GGUF-Q4_K_M

List all available models

lemonade list

How to use from the

Use from the

llama-cpp-python library

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="prithivMLmods/Olmo-3-Think-AIO-GGUF",
	filename="",
)

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

Olmo-3-Think-AIO-GGUF

Olmo-3-32B-Think and Olmo-3-7B-Think are fully open-source dense language models from the Allen Institute for AI, designed for transparent step-by-step reasoning and agentic AI research with inspectable intermediate thought traces. Both models belong to the Olmo 3 family, which features Base, Instruct, and Think variants at the 7B and 32B scales, offering dense transformer architectures optimized for efficient training and long-context processing (up to 65,000 tokens for 32B). The Think models are post-trained to surface explicit reasoning chains, making them ideal for tasks requiring explanation, formal problem decomposition, math reasoning, code generation, and reinforcement learning research. Olmo-3-32B-Think leads open 32B-scale models on benchmarks for reasoning, math, and code, matching or exceeding top models like Qwen3-32B and Gemini-327B, while Olmo-3-7B-Think brings similar transparency and performance to a more hardware-friendly size with efficient long-context support, ensuring broad accessibility for both advanced research and practical deployment scenarios.

Olmo-3-32B-Think [GGUF]

File Name	Quant Type	File Size	File Link
Olmo-3-32B-Think.BF16.gguf	BF16	64.5 GB	Download
Olmo-3-32B-Think.F16.gguf	F16	64.5 GB	Download
Olmo-3-32B-Think.F32.gguf	F32	129 GB	Download
Olmo-3-32B-Think.IQ4_XS.gguf	IQ4_XS	17.5 GB	Download
Olmo-3-32B-Think.Q2_K.gguf	Q2_K	12 GB	Download
Olmo-3-32B-Think.Q3_K_L.gguf	Q3_K_L	16.9 GB	Download
Olmo-3-32B-Think.Q3_K_M.gguf	Q3_K_M	15.6 GB	Download
Olmo-3-32B-Think.Q3_K_S.gguf	Q3_K_S	14.1 GB	Download
Olmo-3-32B-Think.Q4_K_M.gguf	Q4_K_M	19.5 GB	Download
Olmo-3-32B-Think.Q4_K_S.gguf	Q4_K_S	18.4 GB	Download
Olmo-3-32B-Think.Q5_K_M.gguf	Q5_K_M	22.9 GB	Download
Olmo-3-32B-Think.Q5_K_S.gguf	Q5_K_S	22.2 GB	Download
Olmo-3-32B-Think.Q6_K.gguf	Q6_K	26.4 GB	Download
Olmo-3-32B-Think.Q8_0.gguf	Q8_0	34.3 GB	Download
Olmo-3-32B-Think.i1-IQ1_M.gguf	i1-IQ1_M	7.66 GB	Download
Olmo-3-32B-Think.i1-IQ1_S.gguf	i1-IQ1_S	7 GB	Download
Olmo-3-32B-Think.i1-IQ2_M.gguf	i1-IQ2_M	11 GB	Download
Olmo-3-32B-Think.i1-IQ2_S.gguf	i1-IQ2_S	10.1 GB	Download
Olmo-3-32B-Think.i1-IQ2_XS.gguf	i1-IQ2_XS	9.69 GB	Download
Olmo-3-32B-Think.i1-IQ2_XXS.gguf	i1-IQ2_XXS	8.76 GB	Download
Olmo-3-32B-Think.i1-IQ3_M.gguf	i1-IQ3_M	14.5 GB	Download
Olmo-3-32B-Think.i1-IQ3_S.gguf	i1-IQ3_S	14.1 GB	Download
Olmo-3-32B-Think.i1-IQ3_XS.gguf	i1-IQ3_XS	13.4 GB	Download
Olmo-3-32B-Think.i1-IQ3_XXS.gguf	i1-IQ3_XXS	12.5 GB	Download
Olmo-3-32B-Think.i1-IQ4_XS.gguf	i1-IQ4_XS	17.3 GB	Download
Olmo-3-32B-Think.i1-Q2_K.gguf	i1-Q2_K	12 GB	Download
Olmo-3-32B-Think.i1-Q2_K_S.gguf	i1-Q2_K_S	11.2 GB	Download
Olmo-3-32B-Think.i1-Q3_K_L.gguf	i1-Q3_K_L	16.9 GB	Download
Olmo-3-32B-Think.i1-Q3_K_M.gguf	i1-Q3_K_M	15.6 GB	Download
Olmo-3-32B-Think.i1-Q3_K_S.gguf	i1-Q3_K_S	14.1 GB	Download
Olmo-3-32B-Think.i1-Q4_0.gguf	i1-Q4_0	18.3 GB	Download
Olmo-3-32B-Think.i1-Q4_1.gguf	i1-Q4_1	20.3 GB	Download
Olmo-3-32B-Think.i1-Q4_K_M.gguf	i1-Q4_K_M	19.5 GB	Download
Olmo-3-32B-Think.i1-Q4_K_S.gguf	i1-Q4_K_S	18.4 GB	Download
Olmo-3-32B-Think.i1-Q5_K_M.gguf	i1-Q5_K_M	22.9 GB	Download
Olmo-3-32B-Think.i1-Q5_K_S.gguf	i1-Q5_K_S	22.2 GB	Download
Olmo-3-32B-Think.i1-Q6_K.gguf	i1-Q6_K	26.4 GB	Download
Olmo-3-32B-Think.imatrix.gguf	imatrix	15 MB	Download

Olmo-3-7B-Think [GGUF]

File Name	Quant Type	File Size	File Link
Olmo-3-7B-Think.BF16.gguf	BF16	14.6 GB	Download
Olmo-3-7B-Think.F16.gguf	F16	14.6 GB	Download
Olmo-3-7B-Think.F32.gguf	F32	29.2 GB	Download
Olmo-3-7B-Think.IQ4_XS.gguf	IQ4_XS	4.03 GB	Download
Olmo-3-7B-Think.Q2_K.gguf	Q2_K	2.86 GB	Download
Olmo-3-7B-Think.Q3_K_L.gguf	Q3_K_L	3.95 GB	Download
Olmo-3-7B-Think.Q3_K_M.gguf	Q3_K_M	3.65 GB	Download
Olmo-3-7B-Think.Q3_K_S.gguf	Q3_K_S	3.3 GB	Download
Olmo-3-7B-Think.Q4_K_M.gguf	Q4_K_M	4.47 GB	Download
Olmo-3-7B-Think.Q4_K_S.gguf	Q4_K_S	4.25 GB	Download
Olmo-3-7B-Think.Q5_K_M.gguf	Q5_K_M	5.21 GB	Download
Olmo-3-7B-Think.Q5_K_S.gguf	Q5_K_S	5.08 GB	Download
Olmo-3-7B-Think.Q6_K.gguf	Q6_K	5.99 GB	Download
Olmo-3-7B-Think.Q8_0.gguf	Q8_0	7.76 GB	Download
Olmo-3-7B-Think.i1-IQ1_M.gguf	i1-IQ1_M	1.94 GB	Download
Olmo-3-7B-Think.i1-IQ1_S.gguf	i1-IQ1_S	1.82 GB	Download
Olmo-3-7B-Think.i1-IQ2_M.gguf	i1-IQ2_M	2.68 GB	Download
Olmo-3-7B-Think.i1-IQ2_S.gguf	i1-IQ2_S	2.51 GB	Download
Olmo-3-7B-Think.i1-IQ2_XS.gguf	i1-IQ2_XS	2.32 GB	Download
Olmo-3-7B-Think.i1-IQ2_XXS.gguf	i1-IQ2_XXS	2.14 GB	Download
Olmo-3-7B-Think.i1-IQ3_M.gguf	i1-IQ3_M	3.47 GB	Download
Olmo-3-7B-Think.i1-IQ3_S.gguf	i1-IQ3_S	3.3 GB	Download
Olmo-3-7B-Think.i1-IQ3_XS.gguf	i1-IQ3_XS	3.15 GB	Download
Olmo-3-7B-Think.i1-IQ3_XXS.gguf	i1-IQ3_XXS	2.9 GB	Download
Olmo-3-7B-Think.i1-IQ4_NL.gguf	i1-IQ4_NL	4.22 GB	Download
Olmo-3-7B-Think.i1-IQ4_XS.gguf	i1-IQ4_XS	4 GB	Download
Olmo-3-7B-Think.i1-Q2_K.gguf	i1-Q2_K	2.86 GB	Download
Olmo-3-7B-Think.i1-Q2_K_S.gguf	i1-Q2_K_S	2.64 GB	Download
Olmo-3-7B-Think.i1-Q3_K_L.gguf	i1-Q3_K_L	3.95 GB	Download
Olmo-3-7B-Think.i1-Q3_K_M.gguf	i1-Q3_K_M	3.65 GB	Download
Olmo-3-7B-Think.i1-Q3_K_S.gguf	i1-Q3_K_S	3.3 GB	Download
Olmo-3-7B-Think.i1-Q4_0.gguf	i1-Q4_0	4.23 GB	Download
Olmo-3-7B-Think.i1-Q4_1.gguf	i1-Q4_1	4.65 GB	Download
Olmo-3-7B-Think.i1-Q4_K_M.gguf	i1-Q4_K_M	4.47 GB	Download
Olmo-3-7B-Think.i1-Q4_K_S.gguf	i1-Q4_K_S	4.25 GB	Download
Olmo-3-7B-Think.i1-Q5_K_M.gguf	i1-Q5_K_M	5.21 GB	Download
Olmo-3-7B-Think.i1-Q5_K_S.gguf	i1-Q5_K_S	5.08 GB	Download
Olmo-3-7B-Think.i1-Q6_K.gguf	i1-Q6_K	5.99 GB	Download
Olmo-3-7B-Think.imatrix.gguf	imatrix	4.59 MB	Download