Instructions to use Elykdez/vexelflux-models with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use Elykdez/vexelflux-models 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 Elykdez/vexelflux-models:Q4_0
# Run inference directly in the terminal:
llama cli -hf Elykdez/vexelflux-models:Q4_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Elykdez/vexelflux-models:Q4_0
# Run inference directly in the terminal:
llama cli -hf Elykdez/vexelflux-models:Q4_0

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 Elykdez/vexelflux-models:Q4_0
# Run inference directly in the terminal:
./build/bin/llama cli -hf Elykdez/vexelflux-models:Q4_0

Use Docker

docker model run hf.co/Elykdez/vexelflux-models:Q4_0

Llama new
LM Studio
Jan
Ollama
How to use Elykdez/vexelflux-models with Ollama:
```
ollama run hf.co/Elykdez/vexelflux-models:Q4_0
```
Unsloth Desktop

How to use Elykdez/vexelflux-models with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Elykdez/vexelflux-models:Q4_0

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": "Elykdez/vexelflux-models:Q4_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use Elykdez/vexelflux-models with Docker Model Runner:
```
docker model run hf.co/Elykdez/vexelflux-models:Q4_0
```

Lemonade

How to use Elykdez/vexelflux-models with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Elykdez/vexelflux-models:Q4_0

Run and chat with the model

lemonade run user.vexelflux-models-Q4_0

List all available models

lemonade list

Hermes Agent

How to use Elykdez/vexelflux-models with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Elykdez/vexelflux-models:Q4_0

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 Elykdez/vexelflux-models:Q4_0

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use Elykdez/vexelflux-models with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Elykdez/vexelflux-models:Q4_0

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 "Elykdez/vexelflux-models:Q4_0" \
  --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"

VexelFlux model packages

The model packages that VexelFlux downloads when you add a model. Free to download, no account or key needed. Each folder is one package; VexelFlux checks every file against the SHA-256 pinned in its catalog before it uses it.

Package	Folder	Revision	Size	Files
VisionNext	`visionnext/`	`d57d3aaf69bfaab497c0a88c4e7e5bfb57655830`	3.34 GB	12
SharpNext	`sharpnext/`	`ad1271a31ac4e4b3951355f8a2cf279720f4d934`	0.61 GB	15
MoGe-2	`moge2/`	`bfd61e977346480089ae94c4a94283c6b74302a7`	0.42 GB	3

Licenses

Each package's LICENSE.txt holds its licenses and third-party notices:

visionnext/LICENSE.txt: VisionNext (VOSR 2.0) - third-party notices
sharpnext/LICENSE.txt: SharpNext (LPNSR V3) - third-party notices
moge2/LICENSE.txt: MoGe-2 (ViT-B, normal) - third-party notices

Downloads last month: 24

GGUF

Model size

7B params

Architecture

gemma4

Hardware compatibility

4-bit

Inference Providers NEW

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