Instructions to use jondale/Olmo-3-7B-Think-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use jondale/Olmo-3-7B-Think-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 jondale/Olmo-3-7B-Think-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf jondale/Olmo-3-7B-Think-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 jondale/Olmo-3-7B-Think-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf jondale/Olmo-3-7B-Think-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 jondale/Olmo-3-7B-Think-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf jondale/Olmo-3-7B-Think-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 jondale/Olmo-3-7B-Think-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf jondale/Olmo-3-7B-Think-GGUF:Q4_K_M

Use Docker

docker model run hf.co/jondale/Olmo-3-7B-Think-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use jondale/Olmo-3-7B-Think-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "jondale/Olmo-3-7B-Think-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": "jondale/Olmo-3-7B-Think-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/jondale/Olmo-3-7B-Think-GGUF:Q4_K_M

Ollama
How to use jondale/Olmo-3-7B-Think-GGUF with Ollama:
```
ollama run hf.co/jondale/Olmo-3-7B-Think-GGUF:Q4_K_M
```

Unsloth Studio

How to use jondale/Olmo-3-7B-Think-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 jondale/Olmo-3-7B-Think-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 jondale/Olmo-3-7B-Think-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for jondale/Olmo-3-7B-Think-GGUF to start chatting

Docker Model Runner
How to use jondale/Olmo-3-7B-Think-GGUF with Docker Model Runner:
```
docker model run hf.co/jondale/Olmo-3-7B-Think-GGUF:Q4_K_M
```

Lemonade

How to use jondale/Olmo-3-7B-Think-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull jondale/Olmo-3-7B-Think-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Olmo-3-7B-Think-GGUF-Q4_K_M

List all available models

lemonade list

Atomic Chat

Olmo 3 7B Think - GGUF

Quantized from allenai/Olmo-3-7B-Think. All credit to Ai2 - this is a format conversion, with one change to the chat template so llama.cpp can tell the thinking apart from the answer.

Chat template

The stock template puts the opening <think> into the prompt itself:

{{ '<|im_start|>assistant\n<think>' }}

So generation starts already inside a thought, and nothing downstream ever sees one begin. llama.cpp cannot lift the reasoning into reasoning_content, and if you apply a response_format schema the grammar takes the content stream from the first token - which is the same stream the model wants to think in. It then does not think at all.

Deleting the prefill lets the model emit its own opening tag:

-{{ '<|im_start|>assistant\n<think>' }}
+{{ '<|im_start|>assistant\n' }}

That is the whole change. Nothing else moves, and the weights are untouched - the file is byte-identical to the source apart from the template field.

Files

	Size
`olmo-3-7b-think-q4_k_m.gguf`	4.5 GB	the only one so far, ask if you want Q8_0

Running it

llama-server -m olmo-3-7b-think-q4_k_m.gguf --ctx-size 32768 \
    --reasoning on -ngl 99

It thinks at length - 20,000 to 50,000 characters on a tic tac toe move - so give it room. --max-tokens 20000 is not excessive, and a small budget gets you an empty answer rather than a short one.

Made with

gguf_new_metadata.py from llama.cpp b10223, rewriting only tokenizer.chat_template on lmstudio-community/Olmo-3-7B-Think-GGUF. All 355 tensors are theirs, unchanged.