Instructions to use prithivMLmods/Cosmos-Reason2-8B-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use prithivMLmods/Cosmos-Reason2-8B-GGUF with Transformers:

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

pipe = pipeline("image-text-to-text", model="prithivMLmods/Cosmos-Reason2-8B-GGUF")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("prithivMLmods/Cosmos-Reason2-8B-GGUF", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use prithivMLmods/Cosmos-Reason2-8B-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 prithivMLmods/Cosmos-Reason2-8B-GGUF:BF16
# Run inference directly in the terminal:
llama cli -hf prithivMLmods/Cosmos-Reason2-8B-GGUF:BF16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf prithivMLmods/Cosmos-Reason2-8B-GGUF:BF16
# Run inference directly in the terminal:
llama cli -hf prithivMLmods/Cosmos-Reason2-8B-GGUF:BF16

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/Cosmos-Reason2-8B-GGUF:BF16
# Run inference directly in the terminal:
./llama-cli -hf prithivMLmods/Cosmos-Reason2-8B-GGUF:BF16

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/Cosmos-Reason2-8B-GGUF:BF16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf prithivMLmods/Cosmos-Reason2-8B-GGUF:BF16

Use Docker

docker model run hf.co/prithivMLmods/Cosmos-Reason2-8B-GGUF:BF16

LM Studio
Jan

vLLM

How to use prithivMLmods/Cosmos-Reason2-8B-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "prithivMLmods/Cosmos-Reason2-8B-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/Cosmos-Reason2-8B-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/prithivMLmods/Cosmos-Reason2-8B-GGUF:BF16

SGLang

How to use prithivMLmods/Cosmos-Reason2-8B-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/Cosmos-Reason2-8B-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/Cosmos-Reason2-8B-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 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/Cosmos-Reason2-8B-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/Cosmos-Reason2-8B-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"
						}
					}
				]
			}
		]
	}'

Ollama
How to use prithivMLmods/Cosmos-Reason2-8B-GGUF with Ollama:
```
ollama run hf.co/prithivMLmods/Cosmos-Reason2-8B-GGUF:BF16
```

Unsloth Studio

How to use prithivMLmods/Cosmos-Reason2-8B-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/Cosmos-Reason2-8B-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/Cosmos-Reason2-8B-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/Cosmos-Reason2-8B-GGUF to start chatting

How to use prithivMLmods/Cosmos-Reason2-8B-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf prithivMLmods/Cosmos-Reason2-8B-GGUF:BF16

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": "prithivMLmods/Cosmos-Reason2-8B-GGUF:BF16"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use prithivMLmods/Cosmos-Reason2-8B-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf prithivMLmods/Cosmos-Reason2-8B-GGUF:BF16

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default prithivMLmods/Cosmos-Reason2-8B-GGUF:BF16

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use prithivMLmods/Cosmos-Reason2-8B-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf prithivMLmods/Cosmos-Reason2-8B-GGUF:BF16

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "prithivMLmods/Cosmos-Reason2-8B-GGUF:BF16" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

Docker Model Runner
How to use prithivMLmods/Cosmos-Reason2-8B-GGUF with Docker Model Runner:
```
docker model run hf.co/prithivMLmods/Cosmos-Reason2-8B-GGUF:BF16
```

Lemonade

How to use prithivMLmods/Cosmos-Reason2-8B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull prithivMLmods/Cosmos-Reason2-8B-GGUF:BF16

Run and chat with the model

lemonade run user.Cosmos-Reason2-8B-GGUF-BF16

List all available models

lemonade list

prithivMLmods commited on Dec 23, 2025

Commit

1bfa82f

verified ·

1 Parent(s): 0189558

Update README.md

Browse files

Files changed (1) hide show

README.md +21 -1

README.md CHANGED Viewed

@@ -13,4 +13,24 @@ tags:
 # **Cosmos-Reason2-8B-GGUF**
-> NVIDIA Cosmos-Reason2-8B is an 8.767B-parameter open vision-language model post-trained from Qwen3-VL-8B-Instruct under the permissive NVIDIA Open Model License (commercially usable with derivative rights), designed for physical AI, robotics, and embodied reasoning with enhanced spatio-temporal understanding, physics-based common sense, object detection (2D/3D localization, bounding boxes), and 256K token long-context support for video/image inputs at FPS=4. It excels in use cases like video analytics agents (root-cause analysis via NVIDIA VSS Blueprint), data curation/annotation (Cosmos Curator for sensor data), and robot planning (Isaac GR00T-Dreams for synthetic trajectories), generating chain-of-thought responses in <think>/<answer> format for deliberate decision-making in unfamiliar environments across datasets like EgoExo4D, PerceptionTest, IntPhys, and CLEVRER. Optimized for NVIDIA Blackwell/Hopper GPUs (32GB+ VRAM, BF16 on Linux/H100/A100) with Transformers inference (max_tokens=4096), it handles mp4 videos/jpg images for text outputs in robotics, AVs, and industrial ops while noting limitations in complex dynamics like fast motion or occlusions.

 # **Cosmos-Reason2-8B-GGUF**
+> NVIDIA Cosmos-Reason2-8B is an 8.767B-parameter open vision-language model post-trained from Qwen3-VL-8B-Instruct under the permissive NVIDIA Open Model License (commercially usable with derivative rights), designed for physical AI, robotics, and embodied reasoning with enhanced spatio-temporal understanding, physics-based common sense, object detection (2D/3D localization, bounding boxes), and 256K token long-context support for video/image inputs at FPS=4. It excels in use cases like video analytics agents (root-cause analysis via NVIDIA VSS Blueprint), data curation/annotation (Cosmos Curator for sensor data), and robot planning (Isaac GR00T-Dreams for synthetic trajectories), generating chain-of-thought responses in <think>/<answer> format for deliberate decision-making in unfamiliar environments across datasets like EgoExo4D, PerceptionTest, IntPhys, and CLEVRER. Optimized for NVIDIA Blackwell/Hopper GPUs (32GB+ VRAM, BF16 on Linux/H100/A100) with Transformers inference (max_tokens=4096), it handles mp4 videos/jpg images for text outputs in robotics, AVs, and industrial ops while noting limitations in complex dynamics like fast motion or occlusions.
+## Cosmos-Reason2-8B [GGUF]
+| File Name | Quant Type | File Size | File Link |
+| - | - | - | - |
+| Cosmos-Reason2-8B.BF16.gguf | BF16 | 16.4 GB | [Download](https://huggingface.co/prithivMLmods/Cosmos-Reason2-8B-GGUF/blob/main/Cosmos-Reason2-8B.BF16.gguf) |
+| Cosmos-Reason2-8B.F16.gguf | F16 | 16.4 GB | [Download](https://huggingface.co/prithivMLmods/Cosmos-Reason2-8B-GGUF/blob/main/Cosmos-Reason2-8B.F16.gguf) |
+| Cosmos-Reason2-8B.Q8_0.gguf | Q8_0 | 8.71 GB | [Download](https://huggingface.co/prithivMLmods/Cosmos-Reason2-8B-GGUF/blob/main/Cosmos-Reason2-8B.Q8_0.gguf) |
+| Cosmos-Reason2-8B.mmproj-bf16.gguf | mmproj-bf16 | 1.16 GB | [Download](https://huggingface.co/prithivMLmods/Cosmos-Reason2-8B-GGUF/blob/main/Cosmos-Reason2-8B.mmproj-bf16.gguf) |
+| Cosmos-Reason2-8B.mmproj-f16.gguf | mmproj-f16 | 1.16 GB | [Download](https://huggingface.co/prithivMLmods/Cosmos-Reason2-8B-GGUF/blob/main/Cosmos-Reason2-8B.mmproj-f16.gguf) |
+| Cosmos-Reason2-8B.mmproj-q8_0.gguf | mmproj-q8_0 | 752 MB | [Download](https://huggingface.co/prithivMLmods/Cosmos-Reason2-8B-GGUF/blob/main/Cosmos-Reason2-8B.mmproj-q8_0.gguf) |
+## 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):
+![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png)