Instructions to use FoolDev/Janus-35B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use FoolDev/Janus-35B with Transformers:

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

pipe = pipeline("image-text-to-text", model="FoolDev/Janus-35B")
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("FoolDev/Janus-35B", dtype="auto")

llama-cpp-python

How to use FoolDev/Janus-35B with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="FoolDev/Janus-35B",
	filename="Janus-35B-A3B.Q4_K_M.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 FoolDev/Janus-35B with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf FoolDev/Janus-35B:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf FoolDev/Janus-35B:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf FoolDev/Janus-35B:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf FoolDev/Janus-35B: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 FoolDev/Janus-35B:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf FoolDev/Janus-35B: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 FoolDev/Janus-35B:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf FoolDev/Janus-35B:Q4_K_M

Use Docker

docker model run hf.co/FoolDev/Janus-35B:Q4_K_M

LM Studio
Jan

vLLM

How to use FoolDev/Janus-35B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "FoolDev/Janus-35B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "FoolDev/Janus-35B",
		"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/FoolDev/Janus-35B:Q4_K_M

SGLang

How to use FoolDev/Janus-35B 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 "FoolDev/Janus-35B" \
    --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": "FoolDev/Janus-35B",
		"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 "FoolDev/Janus-35B" \
        --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": "FoolDev/Janus-35B",
		"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 FoolDev/Janus-35B with Ollama:
```
ollama run hf.co/FoolDev/Janus-35B:Q4_K_M
```

Unsloth Studio new

How to use FoolDev/Janus-35B 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 FoolDev/Janus-35B 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 FoolDev/Janus-35B to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for FoolDev/Janus-35B to start chatting

Pi new

How to use FoolDev/Janus-35B with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf FoolDev/Janus-35B: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": "FoolDev/Janus-35B:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use FoolDev/Janus-35B with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf FoolDev/Janus-35B: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 FoolDev/Janus-35B:Q4_K_M

Run Hermes

hermes

Docker Model Runner
How to use FoolDev/Janus-35B with Docker Model Runner:
```
docker model run hf.co/FoolDev/Janus-35B:Q4_K_M
```

Lemonade

How to use FoolDev/Janus-35B with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull FoolDev/Janus-35B:Q4_K_M

Run and chat with the model

lemonade run user.Janus-35B-Q4_K_M

List all available models

lemonade list

Janus-35B / banner.svg

FoolDev

Duplicate from FoolDev/Janus-35B

64b629a 9 days ago

preview code

raw

history blame contribute delete

5.1 kB

	<?xml version="1.0" encoding="UTF-8"?>
	<svg xmlns="http://www.w3.org/2000/svg" width="383" height="77" viewBox="0 0 383 77">
	<defs>
	<!-- Tokyo Night gradient: storm blue to night blue -->
	<linearGradient id="bgGrad" x1="0%" y1="0%" x2="100%" y2="100%">
	<stop offset="0%" stop-color="#1a1b26"/>
	<stop offset="50%" stop-color="#24283b"/>
	<stop offset="100%" stop-color="#1f2335"/>
	</linearGradient>
	<!-- Subtle scanline pattern for cyberpunk feel -->
	<pattern id="scan" width="2" height="2" patternUnits="userSpaceOnUse">
	<rect width="2" height="1" fill="#1a1b26" opacity="0.0"/>
	<rect y="1" width="2" height="1" fill="#7aa2f7" opacity="0.04"/>
	</pattern>
	<!-- Token-stream scan beam: gradient sweeps along the lower edge -->
	<linearGradient id="beam" x1="0%" y1="0%" x2="100%" y2="0%">
	<stop offset="0%" stop-color="#7aa2f7" stop-opacity="0"/>
	<stop offset="50%" stop-color="#7dcfff" stop-opacity="0.55"/>
	<stop offset="100%" stop-color="#7aa2f7" stop-opacity="0"/>
	</linearGradient>
	</defs>

	<!-- Background -->
	<rect width="383" height="77" fill="url(#bgGrad)"/>
	<rect width="383" height="77" fill="url(#scan)"/>

	<!-- Left accent bar: Tokyo Night cyan -->
	<rect x="0" y="0" width="3" height="77" fill="#7dcfff"/>

	<!-- MoE expert-routing dot grid (12 cells; staggered opacity cycles
	evoke the 8-of-256 sparse activation pattern in the real model). -->
	<g>
	<circle cx="320" cy="14" r="1.6" fill="#bb9af7" fill-opacity="0.15">
	<animate attributeName="fill-opacity" values="0.15;1;0.15" dur="2.4s" begin="0s" repeatCount="indefinite"/>
	</circle>
	<circle cx="330" cy="14" r="1.6" fill="#7aa2f7" fill-opacity="0.15">
	<animate attributeName="fill-opacity" values="0.15;0.85;0.15" dur="2.6s" begin="0.3s" repeatCount="indefinite"/>
	</circle>
	<circle cx="340" cy="14" r="1.6" fill="#bb9af7" fill-opacity="0.15">
	<animate attributeName="fill-opacity" values="0.15;0.9;0.15" dur="3.0s" begin="0.7s" repeatCount="indefinite"/>
	</circle>
	<circle cx="350" cy="14" r="1.6" fill="#7dcfff" fill-opacity="0.15">
	<animate attributeName="fill-opacity" values="0.15;0.9;0.15" dur="2.8s" begin="1.1s" repeatCount="indefinite"/>
	</circle>
	<circle cx="360" cy="14" r="1.6" fill="#7aa2f7" fill-opacity="0.15">
	<animate attributeName="fill-opacity" values="0.15;0.85;0.15" dur="3.2s" begin="0.5s" repeatCount="indefinite"/>
	</circle>
	<circle cx="370" cy="14" r="1.6" fill="#bb9af7" fill-opacity="0.15">
	<animate attributeName="fill-opacity" values="0.15;1;0.15" dur="2.7s" begin="1.5s" repeatCount="indefinite"/>
	</circle>
	<circle cx="320" cy="24" r="1.6" fill="#7aa2f7" fill-opacity="0.15">
	<animate attributeName="fill-opacity" values="0.15;0.85;0.15" dur="2.9s" begin="0.9s" repeatCount="indefinite"/>
	</circle>
	<circle cx="330" cy="24" r="1.6" fill="#bb9af7" fill-opacity="0.15">
	<animate attributeName="fill-opacity" values="0.15;0.95;0.15" dur="3.3s" begin="1.7s" repeatCount="indefinite"/>
	</circle>
	<circle cx="340" cy="24" r="1.6" fill="#7dcfff" fill-opacity="0.15">
	<animate attributeName="fill-opacity" values="0.15;0.85;0.15" dur="2.5s" begin="0.2s" repeatCount="indefinite"/>
	</circle>
	<circle cx="350" cy="24" r="1.6" fill="#bb9af7" fill-opacity="0.15">
	<animate attributeName="fill-opacity" values="0.15;0.9;0.15" dur="3.1s" begin="1.3s" repeatCount="indefinite"/>
	</circle>
	<circle cx="360" cy="24" r="1.6" fill="#7aa2f7" fill-opacity="0.15">
	<animate attributeName="fill-opacity" values="0.15;1;0.15" dur="2.8s" begin="0.6s" repeatCount="indefinite"/>
	</circle>
	<circle cx="370" cy="24" r="1.6" fill="#bb9af7" fill-opacity="0.15">
	<animate attributeName="fill-opacity" values="0.15;0.85;0.15" dur="2.5s" begin="2.0s" repeatCount="indefinite"/>
	</circle>
	</g>

	<!-- Wordmark: JANUS-35B -->
	<text x="20" y="38"
	font-family="ui-monospace, 'SF Mono', 'Cascadia Mono', 'JetBrains Mono', Menlo, Consolas, monospace"
	font-size="26"
	font-weight="700"
	letter-spacing="2"
	fill="#c0caf5">JANUS<tspan fill="#7aa2f7">-35B</tspan></text>

	<!-- Subtitle -->
	<text x="20" y="58"
	font-family="ui-monospace, 'SF Mono', 'Cascadia Mono', 'JetBrains Mono', Menlo, Consolas, monospace"
	font-size="10"
	font-weight="400"
	letter-spacing="1.5"
	fill="#9aa5ce">Qwen 3.6 · MoE 35B/3B · Opus 4.7 distilled</text>

	<!-- Token-stream scan beam: sweeps left-to-right along the bottom edge,
	evoking the cursor of an LLM generating tokens in real time. -->
	<rect x="-100" y="73" width="100" height="1.2" fill="url(#beam)" opacity="0.85">
	<animate attributeName="x" values="-100;500" dur="4s" repeatCount="indefinite"/>
	</rect>

	<!-- Right accent: status dot (terminal cursor) -->
	<rect x="370" y="56" width="6" height="10" fill="#9ece6a">
	<animate attributeName="opacity" values="1;0.3;1" dur="2s" repeatCount="indefinite"/>
	</rect>
	</svg>