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

Libraries

How to use janhq/Jan-v2-VL-max-gguf with Transformers:

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

pipe = pipeline("image-text-to-text", model="janhq/Jan-v2-VL-max-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("janhq/Jan-v2-VL-max-gguf", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use janhq/Jan-v2-VL-max-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 janhq/Jan-v2-VL-max-gguf:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf janhq/Jan-v2-VL-max-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 janhq/Jan-v2-VL-max-gguf:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf janhq/Jan-v2-VL-max-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 janhq/Jan-v2-VL-max-gguf:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf janhq/Jan-v2-VL-max-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 janhq/Jan-v2-VL-max-gguf:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf janhq/Jan-v2-VL-max-gguf:Q4_K_M

Use Docker

docker model run hf.co/janhq/Jan-v2-VL-max-gguf:Q4_K_M

LM Studio
Jan

vLLM

How to use janhq/Jan-v2-VL-max-gguf with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "janhq/Jan-v2-VL-max-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": "janhq/Jan-v2-VL-max-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/janhq/Jan-v2-VL-max-gguf:Q4_K_M

SGLang

How to use janhq/Jan-v2-VL-max-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 "janhq/Jan-v2-VL-max-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": "janhq/Jan-v2-VL-max-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 "janhq/Jan-v2-VL-max-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": "janhq/Jan-v2-VL-max-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 janhq/Jan-v2-VL-max-gguf with Ollama:
```
ollama run hf.co/janhq/Jan-v2-VL-max-gguf:Q4_K_M
```
Unsloth Desktop

How to use janhq/Jan-v2-VL-max-gguf with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf janhq/Jan-v2-VL-max-gguf:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "janhq/Jan-v2-VL-max-gguf:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use janhq/Jan-v2-VL-max-gguf with Docker Model Runner:
```
docker model run hf.co/janhq/Jan-v2-VL-max-gguf:Q4_K_M
```

Lemonade

How to use janhq/Jan-v2-VL-max-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull janhq/Jan-v2-VL-max-gguf:Q4_K_M

Run and chat with the model

lemonade run user.Jan-v2-VL-max-gguf-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use janhq/Jan-v2-VL-max-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 janhq/Jan-v2-VL-max-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 janhq/Jan-v2-VL-max-gguf:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use janhq/Jan-v2-VL-max-gguf with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf janhq/Jan-v2-VL-max-gguf:Q4_K_M

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 "janhq/Jan-v2-VL-max-gguf:Q4_K_M" \
  --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"

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

Overview

Jan-v2-VL-max extends the Jan-v2-VL family to a 30B-parameter vision–language model focused on long-horizon execution. This release scales model capacity and applies LoRA-based RLVR to improve stability over many steps with low error accumulation. For evaluation, we continue to use The Illusion of Diminishing Returns: Measuring Long-Horizon Execution in LLMs, which emphasizes execution length rather than knowledge recall.

Intended Use

Tasks where the plan and/or knowledge can be provided up front, and success hinges on stable, many-step execution with minimal drift:

Agentic automation & UI control: Stepwise operation in browsers/desktop apps with screenshot grounding and tool calls via Jan Browser MCP.

Model Performance

Evaluated under FP8 inference, Jan-v2-VL-max vs. Qwen3-VL-30B-A3B-Thinking shows no regressions and small gains on several tasks, with the largest improvements in long-horizon execution. Our FP8 build maintains accuracy while reducing memory footprint and latency.

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-FP8 \
    --host 0.0.0.0 \
    --port 1234 \
    -dp 1 \
    --enable-auto-tool-choice \
    --tool-call-parser hermes \
    --reasoning-parser deepseek_r1

Using llama.cpp:

llama-server --model Jan-v2-VL-max-Q8_0.gguf \
    --vision-model-path Jan-v2-VL-max-mmproj.gguf \
    --host 0.0.0.0 \
    --port 1234 \
    --jinja \
    --no-context-shift

Recommended Parameters

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

temperature: 1.0
top_p: 0.95
top_k: 20
repetition_penalty: 1.0
presence_penalty: 1.5

🤝 Community & Support

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

📄 Citation

Updated Soon

Downloads last month: 660

GGUF

Model size

31B params

Architecture

qwen3vlmoe

Hardware compatibility

3-bit

4-bit

5-bit

6-bit

8-bit

View +1 variant

Model tree for janhq/Jan-v2-VL-max-gguf

Base model

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

Quantized

(32)

this model

Collection including janhq/Jan-v2-VL-max-gguf

Jan-v2-VL

Collection

Jan-v2-VL: a family of VLM focused on reliable, many-step task execution. • 9 items • Updated Mar 13 • 40

Paper for janhq/Jan-v2-VL-max-gguf

The Illusion of Diminishing Returns: Measuring Long Horizon Execution in LLMs

Paper • 2509.09677 • Published Sep 11, 2025 • 37