Instructions to use earth-demon/CapRL-InternVL3.5-8B-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 earth-demon/CapRL-InternVL3.5-8B-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 earth-demon/CapRL-InternVL3.5-8B-GGUF:F16
# Run inference directly in the terminal:
llama cli -hf earth-demon/CapRL-InternVL3.5-8B-GGUF:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf earth-demon/CapRL-InternVL3.5-8B-GGUF:F16
# Run inference directly in the terminal:
llama cli -hf earth-demon/CapRL-InternVL3.5-8B-GGUF:F16

Build from source code

git clone https://github.com/ggml-org/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-app
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama serve -hf earth-demon/CapRL-InternVL3.5-8B-GGUF:F16
# Run inference directly in the terminal:
./build/bin/llama cli -hf earth-demon/CapRL-InternVL3.5-8B-GGUF:F16

Use Docker

docker model run hf.co/earth-demon/CapRL-InternVL3.5-8B-GGUF:F16

Llama new
LM Studio
Jan

vLLM

How to use earth-demon/CapRL-InternVL3.5-8B-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "earth-demon/CapRL-InternVL3.5-8B-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": "earth-demon/CapRL-InternVL3.5-8B-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/earth-demon/CapRL-InternVL3.5-8B-GGUF:F16

Ollama
How to use earth-demon/CapRL-InternVL3.5-8B-GGUF with Ollama:
```
ollama run hf.co/earth-demon/CapRL-InternVL3.5-8B-GGUF:F16
```
Unsloth Desktop
Docker Model Runner
How to use earth-demon/CapRL-InternVL3.5-8B-GGUF with Docker Model Runner:
```
docker model run hf.co/earth-demon/CapRL-InternVL3.5-8B-GGUF:F16
```

Lemonade

How to use earth-demon/CapRL-InternVL3.5-8B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull earth-demon/CapRL-InternVL3.5-8B-GGUF:F16

Run and chat with the model

lemonade run user.CapRL-InternVL3.5-8B-GGUF-F16

List all available models

lemonade list

Atomic Chat

转换脚本来源：Jobaar/CapRL-InternVL3.5-8B-GGUF >> script ，原仓库没提供 Q8 和 F16 权重，自己转换了。。。

Downloads last month: 20

GGUF

Model size

8B params

Architecture

qwen3

Hardware compatibility

8-bit

16-bit

Model tree for earth-demon/CapRL-InternVL3.5-8B-GGUF

Base model

OpenGVLab/InternVL3_5-8B-Pretrained

Finetuned

OpenGVLab/InternVL3_5-8B-Instruct

Finetuned

OpenGVLab/InternVL3_5-8B-MPO

Finetuned

OpenGVLab/InternVL3_5-8B

Finetuned

internlm/CapRL-InternVL3.5-8B

Quantized

(2)

this model

earth-demon
/

CapRL-InternVL3.5-8B-GGUF

Model tree for earth-demon/CapRL-InternVL3.5-8B-GGUF

Dataset used to train earth-demon/CapRL-InternVL3.5-8B-GGUF