Instructions to use Jwuthrich/selfjev-4b-vision-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 Jwuthrich/selfjev-4b-vision-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 Jwuthrich/selfjev-4b-vision-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Jwuthrich/selfjev-4b-vision-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 Jwuthrich/selfjev-4b-vision-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Jwuthrich/selfjev-4b-vision-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 Jwuthrich/selfjev-4b-vision-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Jwuthrich/selfjev-4b-vision-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 Jwuthrich/selfjev-4b-vision-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Jwuthrich/selfjev-4b-vision-GGUF:Q4_K_M

Use Docker

docker model run hf.co/Jwuthrich/selfjev-4b-vision-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use Jwuthrich/selfjev-4b-vision-GGUF with Ollama:
```
ollama run hf.co/Jwuthrich/selfjev-4b-vision-GGUF:Q4_K_M
```
Unsloth Desktop

How to use Jwuthrich/selfjev-4b-vision-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Jwuthrich/selfjev-4b-vision-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": "Jwuthrich/selfjev-4b-vision-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use Jwuthrich/selfjev-4b-vision-GGUF with Docker Model Runner:
```
docker model run hf.co/Jwuthrich/selfjev-4b-vision-GGUF:Q4_K_M
```

Lemonade

How to use Jwuthrich/selfjev-4b-vision-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Jwuthrich/selfjev-4b-vision-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.selfjev-4b-vision-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use Jwuthrich/selfjev-4b-vision-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 Jwuthrich/selfjev-4b-vision-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 Jwuthrich/selfjev-4b-vision-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use Jwuthrich/selfjev-4b-vision-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Jwuthrich/selfjev-4b-vision-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 "Jwuthrich/selfjev-4b-vision-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"

selfjev-4b-vision, GGUF for Ollama

SelfJev reads one text (or image) and answers many yes/no, choice, score and multi-select questions about it. These are the GGUF files of the merged model selfjev-4b-vision-merged, converted with llama.cpp: Q8_0, Q4_K_M and the vision projector mmproj-selfjev-4b-vision-bf16.gguf.

ollama pull hf.co/Jwuthrich/selfjev-4b-vision-GGUF:Q8_0
pip install "selfjev[ollama]"
selfjev serve --engine ollama --ollama-model hf.co/Jwuthrich/selfjev-4b-vision-GGUF:Q8_0

The model is a scorer, not a chat model: it reads the logprob of yes against no after a fixed prompt, one request per option. Use it through selfjev serve --engine ollama (docs), which speaks Jev's API; ollama run alone will not give decisions.

	eval2	eval_llm	images
tree engine, bf16 (reference)	96.1	92.5	90.4
Ollama Q8_0	95.7	92.7	89.4
Ollama Q4_K_M	95.7	91.9	not run

Measured through Ollama 0.35.0 on an L40S, 2026-10-01 (reports). Slower than the tree engine for many questions per text (one request per option).

Downloads last month: 172

GGUF

Model size

4B params

Architecture

qwen35

Hardware compatibility

4-bit

8-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for Jwuthrich/selfjev-4b-vision-GGUF

Base model

Qwen/Qwen3.5-4B-Base

Finetuned

Qwen/Qwen3.5-4B

Finetuned

Jwuthrich/selfjev-4b-vision-merged

Quantized

(1)

this model