Instructions to use VrKnight/JEV-9B-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 VrKnight/JEV-9B-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 VrKnight/JEV-9B-GGUF:BF16
# Run inference directly in the terminal:
llama cli -hf VrKnight/JEV-9B-GGUF:BF16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf VrKnight/JEV-9B-GGUF:BF16
# Run inference directly in the terminal:
llama cli -hf VrKnight/JEV-9B-GGUF:BF16

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 VrKnight/JEV-9B-GGUF:BF16
# Run inference directly in the terminal:
./build/bin/llama cli -hf VrKnight/JEV-9B-GGUF:BF16

Use Docker

docker model run hf.co/VrKnight/JEV-9B-GGUF:BF16

Llama new
LM Studio
Jan
Ollama
How to use VrKnight/JEV-9B-GGUF with Ollama:
```
ollama run hf.co/VrKnight/JEV-9B-GGUF:BF16
```
Unsloth Desktop

How to use VrKnight/JEV-9B-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf VrKnight/JEV-9B-GGUF:BF16

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": "VrKnight/JEV-9B-GGUF:BF16"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use VrKnight/JEV-9B-GGUF with Docker Model Runner:
```
docker model run hf.co/VrKnight/JEV-9B-GGUF:BF16
```

Lemonade

How to use VrKnight/JEV-9B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull VrKnight/JEV-9B-GGUF:BF16

Run and chat with the model

lemonade run user.JEV-9B-GGUF-BF16

List all available models

lemonade list

Hermes Agent

How to use VrKnight/JEV-9B-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 VrKnight/JEV-9B-GGUF:BF16

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 VrKnight/JEV-9B-GGUF:BF16

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use VrKnight/JEV-9B-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf VrKnight/JEV-9B-GGUF:BF16

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 "VrKnight/JEV-9B-GGUF:BF16" \
  --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"

JEV-9B-GGUF (Merged System-1 Backbone + Multimodal Vision)

GGUF quantizations of autotrust/JEV-9B (System-1 LoRA merged into the Qwen/Qwen3.5-9B backbone) and its companion multimodal vision projector (mmproj).

Available GGUF Files

File	Size	Format	Description
`JEV-9B-Q8_0.gguf`	8.86 GiB	`Q8_0`	Quantized LoRA-merged JEV-9B trunk (recommended for 12 GB+ GPUs)
`JEV-9B-BF16.gguf`	16.68 GiB	`BF16`	Full-precision `BF16` LoRA-merged JEV-9B trunk
`mmproj-JEV-9B-BF16.gguf`	879 MiB	`BF16`	Companion `Qwen3.5-9B` ViT + vision merger for multimodal image inputs

Native C++ System-1 Runtime & HTTP Server (`llama-jev`)

Standard llama.cpp only runs generative text chat (System-2) and does not include the JEV System-1 calibrated decision head (choice, bool/noul, score 0–5 with calibrated probabilities and expected values).

A standalone native C++ runtime & persistent HTTP server (llama-jev-cli / --port 8080, POST /v1/decide) with the JEV-9B System-1 decision head embedded directly in the binary (no Python or vLLM required, Windows/Linux, text + multimodal images) is available:

Parity vs PyTorch BF16 Reference: 100% argmax parity (max |dP| = 0.00133 on BF16, 0.0101 on Q8_0).
Capabilities: Multi-question batching, multimodal image inputs (--mmproj), persistent /v1/decide HTTP server, and zero external dependencies.
Licensing / Binary Access: Open a discussion on VrKnight/JEV-9B-GGUF for commercial or indie binary licensing.

Downloads last month: 230

GGUF

Model size

9B params

Architecture

qwen35

Hardware compatibility

8-bit

16-bit

Inference Providers NEW

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

Model tree for VrKnight/JEV-9B-GGUF

Base model

Qwen/Qwen3.5-9B-Base

Finetuned

Qwen/Qwen3.5-9B

Quantized

(677)

this model

JEV-9B-GGUF (Merged System-1 Backbone + Multimodal Vision)

Available GGUF Files

Native C++ System-1 Runtime & HTTP Server (llama-jev)

Model tree for VrKnight/JEV-9B-GGUF

Native C++ System-1 Runtime & HTTP Server (`llama-jev`)