Instructions to use RhinoWithAcape/Cosmos-Reason2-32B-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use RhinoWithAcape/Cosmos-Reason2-32B-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="RhinoWithAcape/Cosmos-Reason2-32B-GGUF",
	filename="Cosmos-Reason2-32B.Q2_K.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": [
				{
					"type": "text",
					"text": "Describe this image in one sentence."
				},
				{
					"type": "image_url",
					"image_url": {
						"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
					}
				}
			]
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use RhinoWithAcape/Cosmos-Reason2-32B-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf RhinoWithAcape/Cosmos-Reason2-32B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf RhinoWithAcape/Cosmos-Reason2-32B-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 RhinoWithAcape/Cosmos-Reason2-32B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf RhinoWithAcape/Cosmos-Reason2-32B-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 RhinoWithAcape/Cosmos-Reason2-32B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf RhinoWithAcape/Cosmos-Reason2-32B-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 RhinoWithAcape/Cosmos-Reason2-32B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf RhinoWithAcape/Cosmos-Reason2-32B-GGUF:Q4_K_M

Use Docker

docker model run hf.co/RhinoWithAcape/Cosmos-Reason2-32B-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use RhinoWithAcape/Cosmos-Reason2-32B-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "RhinoWithAcape/Cosmos-Reason2-32B-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": "RhinoWithAcape/Cosmos-Reason2-32B-GGUF",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/RhinoWithAcape/Cosmos-Reason2-32B-GGUF:Q4_K_M

Ollama
How to use RhinoWithAcape/Cosmos-Reason2-32B-GGUF with Ollama:
```
ollama run hf.co/RhinoWithAcape/Cosmos-Reason2-32B-GGUF:Q4_K_M
```

Unsloth Studio new

How to use RhinoWithAcape/Cosmos-Reason2-32B-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 RhinoWithAcape/Cosmos-Reason2-32B-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 RhinoWithAcape/Cosmos-Reason2-32B-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for RhinoWithAcape/Cosmos-Reason2-32B-GGUF to start chatting

Pi new

How to use RhinoWithAcape/Cosmos-Reason2-32B-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf RhinoWithAcape/Cosmos-Reason2-32B-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": "Cosmos-Reason2-32B-GGUF"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use RhinoWithAcape/Cosmos-Reason2-32B-GGUF with Docker Model Runner:
```
docker model run hf.co/RhinoWithAcape/Cosmos-Reason2-32B-GGUF:Q4_K_M
```

Lemonade

How to use RhinoWithAcape/Cosmos-Reason2-32B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull RhinoWithAcape/Cosmos-Reason2-32B-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Cosmos-Reason2-32B-GGUF-Q4_K_M

List all available models

lemonade list

Cosmos-Reason2-32B — GGUF

GGUF conversion of nvidia/Cosmos-Reason2-32B, NVIDIA's open reasoning vision-language model for Physical AI and robotics — space, time, and physics understanding for embodied reasoning.

Built on Qwen3-VL-32B-Instruct and post-trained for video/image-grounded reasoning at FPS=4.

Licensed by NVIDIA Corporation under the NVIDIA Open Model License.

Quants

Quant	Size	Notes
Q2_K	12.3 GB	Fits a 16 GB GPU — biggest size hit, still useful for reasoning
Q3_K_M	16.0 GB	Sweet spot for 16-20 GB GPUs
Q4_K_M	19.8 GB	Recommended default — fits a 24 GB GPU
Q5_K_M	23.2 GB	Quality bump, needs 32 GB
Q6_K	26.9 GB	Near-lossless
Q8_0	34.8 GB	Reference quality

Plus mmproj-Cosmos-Reason2-32B.f16.gguf (1.2 GB) — the Qwen3-VL vision tower projector required for image and video input. Pair it with any of the quants above.

Quick start (llama.cpp — text only)

./build/bin/llama-cli \
    -m Cosmos-Reason2-32B.Q4_K_M.gguf \
    -p "Explain why a ball rolls down a slope, step by step." \
    -n 200 --temp 0.6

Quick start (llama.cpp — vision)

The mmproj projector enables image and video reasoning. Use llama-mtmd-cli:

./build/bin/llama-mtmd-cli \
    -m Cosmos-Reason2-32B.Q4_K_M.gguf \
    --mmproj mmproj-Cosmos-Reason2-32B.f16.gguf \
    --image path/to/image.jpg \
    -p "Describe what is happening in this scene and predict what comes next."

For video, pass an MP4 with --video. NVIDIA recommends FPS=4.

Quick start (Ollama)

hf download RhinoWithAcape/Cosmos-Reason2-32B-GGUF \
    Cosmos-Reason2-32B.Q4_K_M.gguf Modelfile --local-dir ./model
cd ./model
ollama create cosmos-reason2-32b:Q4_K_M -f Modelfile
ollama run cosmos-reason2-32b:Q4_K_M "Hello"

Note: at time of writing, Ollama vision support for the Qwen3-VL family lags llama.cpp. For full image/video reasoning, prefer llama-mtmd-cli with the mmproj file.

Conversion details

Source: nvidia/Cosmos-Reason2-32B (BF16 safetensors).
Tool: llama.cpp convert_hf_to_gguf.py with the Qwen3VLForConditionalGeneration text + mmproj split.
Chat template (tokenizer_config.json) is embedded in the GGUF — works with the standard <|im_start|> / <|im_end|> Qwen turn structure.
Native context length: 262 144 tokens. The Modelfile defaults to a conservative 8 192 — raise num_ctx if you have the VRAM.
Recommended sampling for reasoning: temperature ~ 0.6, top_p ~ 0.9.

License

Released under the NVIDIA Open Model License. You must comply with that license when using these GGUF weights, including the Trustworthy AI restrictions and the attribution requirement above.

RhinoWithAcape

Downloads last month: 311

GGUF

Model size

33B params

Architecture

qwen3vl

Hardware compatibility

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

Model tree for RhinoWithAcape/Cosmos-Reason2-32B-GGUF

Base model

Qwen/Qwen3-VL-32B-Instruct

Finetuned

nvidia/Cosmos-Reason2-32B

Quantized

(6)

this model