Instructions to use cmh/Jan-v2-VL-max-Instruct-FP8-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use cmh/Jan-v2-VL-max-Instruct-FP8-GGUF with Transformers:

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

pipe = pipeline("image-text-to-text", model="cmh/Jan-v2-VL-max-Instruct-FP8-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("cmh/Jan-v2-VL-max-Instruct-FP8-GGUF", dtype="auto")

llama-cpp-python

How to use cmh/Jan-v2-VL-max-Instruct-FP8-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="cmh/Jan-v2-VL-max-Instruct-FP8-GGUF",
	filename="Jan-v2-VL-max-Instruct-FP8_F16.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 cmh/Jan-v2-VL-max-Instruct-FP8-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf cmh/Jan-v2-VL-max-Instruct-FP8-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf cmh/Jan-v2-VL-max-Instruct-FP8-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 cmh/Jan-v2-VL-max-Instruct-FP8-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf cmh/Jan-v2-VL-max-Instruct-FP8-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 cmh/Jan-v2-VL-max-Instruct-FP8-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf cmh/Jan-v2-VL-max-Instruct-FP8-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 cmh/Jan-v2-VL-max-Instruct-FP8-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf cmh/Jan-v2-VL-max-Instruct-FP8-GGUF:Q4_K_M

Use Docker

docker model run hf.co/cmh/Jan-v2-VL-max-Instruct-FP8-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use cmh/Jan-v2-VL-max-Instruct-FP8-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "cmh/Jan-v2-VL-max-Instruct-FP8-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": "cmh/Jan-v2-VL-max-Instruct-FP8-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/cmh/Jan-v2-VL-max-Instruct-FP8-GGUF:Q4_K_M

SGLang

How to use cmh/Jan-v2-VL-max-Instruct-FP8-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 "cmh/Jan-v2-VL-max-Instruct-FP8-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": "cmh/Jan-v2-VL-max-Instruct-FP8-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 "cmh/Jan-v2-VL-max-Instruct-FP8-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": "cmh/Jan-v2-VL-max-Instruct-FP8-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 cmh/Jan-v2-VL-max-Instruct-FP8-GGUF with Ollama:
```
ollama run hf.co/cmh/Jan-v2-VL-max-Instruct-FP8-GGUF:Q4_K_M
```

Unsloth Studio new

How to use cmh/Jan-v2-VL-max-Instruct-FP8-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 cmh/Jan-v2-VL-max-Instruct-FP8-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 cmh/Jan-v2-VL-max-Instruct-FP8-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for cmh/Jan-v2-VL-max-Instruct-FP8-GGUF to start chatting

Pi new

How to use cmh/Jan-v2-VL-max-Instruct-FP8-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf cmh/Jan-v2-VL-max-Instruct-FP8-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": "cmh/Jan-v2-VL-max-Instruct-FP8-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use cmh/Jan-v2-VL-max-Instruct-FP8-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf cmh/Jan-v2-VL-max-Instruct-FP8-GGUF:Q4_K_M

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 cmh/Jan-v2-VL-max-Instruct-FP8-GGUF:Q4_K_M

Run Hermes

hermes

Docker Model Runner
How to use cmh/Jan-v2-VL-max-Instruct-FP8-GGUF with Docker Model Runner:
```
docker model run hf.co/cmh/Jan-v2-VL-max-Instruct-FP8-GGUF:Q4_K_M
```

Lemonade

How to use cmh/Jan-v2-VL-max-Instruct-FP8-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull cmh/Jan-v2-VL-max-Instruct-FP8-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Jan-v2-VL-max-Instruct-FP8-GGUF-Q4_K_M

List all available models

lemonade list

GGUF quantization of JJan-v2-VL-max-Instruct-FP8, mmproj included.

llama-server -m Jan-v2-VL-max-Instruct-FP8_Q8_0.gguf --mmproj mmproj-Jan-v2-VL-max-Instruct-FP8_F16.gguf

Jan-v2-VL-max-Instruct-FP8

	Quant type	File Size
Jan-v2-VL-max-Instruct-FP8_Q4_K_S	4 bits per weight	17.5 GB
Jan-v2-VL-max-Instruct-FP8_Q4_K_M	4 bits per weight	18.6 GB
Jan-v2-VL-max-Instruct-FP8_Q5_K_S	5 bits per weight	21.1 GB
Jan-v2-VL-max-Instruct-FP8_Q5_K_M	5 bits per weight	21.7 GB
Jan-v2-VL-max-Instruct-FP8_Q6_K	6 bits per weight	25.1 GB
Jan-v2-VL-max-Instruct-FP8_Q8_0	8 bits per weight	32.5 GB
Jan-v2-VL-max-Instruct-FP8_F16	16 bits per weight	61.1 GB

mmproj-Jan-v2-VL-max-Instruct-FP8

	Quant type	File Size
mmproj-Jan-v2-VL-max-Instruct-FP8_Q8_0	8 bits per weight	712 MB
mmproj-Jan-v2-VL-max-Instruct-FP8_F16	16 bits per weight	1.08 GB

Jan-v2-VL: Multimodal Agent for Long-Horizon Tasks

Overview

Jan-v2-VL-max-Intruct extends the Jan-v2-VL family to a 30B-parameter vision–language model focused on research capability.

Local Deployment

Jan Web

Hosted on Jan Web — use the model directly at chat.jan.ai

Local Deployment

Using vLLM: We recommend vLLM for serving and inference. All reported results were run with vLLM 0.12.0. For FP8 deployment, we used llm-compressor built from source. Please pin transformers==4.57.1 for compatibility.

# Exact versions used in our evals
pip install vllm==0.12.0
pip install transformers==4.57.1
pip install "git+https://github.com/vllm-project/llm-compressor.git@1abfd9eb34a2941e82f47cbd595f1aab90280c80"

vllm serve Menlo/Jan-v2-VL-max-Instruct-FP8 \
    --host 0.0.0.0 \
    --port 1234 \
    -dp 1 \
    --enable-auto-tool-choice \
    --tool-call-parser hermes

Recommended Parameters

For optimal performance in agentic and general tasks, we recommend the following inference parameters:

temperature: 0.7
top_p: 0.8
top_k: 20
repetition_penalty: 1.0
presence_penalty: 0.0

🤝 Community & Support

Discussions: Hugging Face Community
Jan App: Learn more about the Jan App at jan.ai

📄 Citation

Updated Soon

Downloads last month: 86

GGUF

Model size

31B params

Architecture

qwen3vlmoe

Hardware compatibility

4-bit

5-bit

6-bit

8-bit

16-bit

Model tree for cmh/Jan-v2-VL-max-Instruct-FP8-GGUF

Base model

Qwen/Qwen3-VL-30B-A3B-Instruct

Quantized

(58)

this model