Instructions to use Noname010101/media-extras with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use Noname010101/media-extras 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 Noname010101/media-extras:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Noname010101/media-extras:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Noname010101/media-extras:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Noname010101/media-extras:Q4_K_M

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 Noname010101/media-extras:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama cli -hf Noname010101/media-extras:Q4_K_M

Use Docker

docker model run hf.co/Noname010101/media-extras:Q4_K_M

Llama new
LM Studio
Jan
Ollama
How to use Noname010101/media-extras with Ollama:
```
ollama run hf.co/Noname010101/media-extras:Q4_K_M
```
Unsloth Desktop

How to use Noname010101/media-extras with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Noname010101/media-extras: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": "Noname010101/media-extras:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use Noname010101/media-extras with Docker Model Runner:
```
docker model run hf.co/Noname010101/media-extras:Q4_K_M
```

Lemonade

How to use Noname010101/media-extras with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Noname010101/media-extras:Q4_K_M

Run and chat with the model

lemonade run user.media-extras-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use Noname010101/media-extras with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Noname010101/media-extras: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 Noname010101/media-extras:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use Noname010101/media-extras with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Noname010101/media-extras: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 "Noname010101/media-extras: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"

media-extras

Mirror of the extra model weights used by the video generation pod image (ComfyUI + Wan 2.1 / SVI 2.0 Pro + RIFE + Real-ESRGAN). Public, so pods do not depend on third-party repos at boot. Files are unmodified copies of the originals; only the lightx2v LoRA filename was changed to the name the image expects (original name in the table).

Layout: svi/, rife/, upscale/, vace/, t2v/, text_encoders/, vae/, loras/.

Files

path	size (bytes)	sha256	original source / license
`loras/lightx2v_t2v_14b_rank32.safetensors`	316822496	`914fafa5dded72e6c470d6f764b97fe4d71567dae7cc01d1181b310efd5c37a6`	https://huggingface.co/Kijai/WanVideo_comfy (lightx2v distill LoRA, upstream lightx2v/Wan2.1-Distill-Loras Apache-2.0; original name Wan21_T2V_14B_lightx2v_cfg_step_distill_lora_rank32.safetensors, renamed)
`rife/rife49.pth`	21345274	`e55fd00f3cc184e3c65961f4bb827a9da022e78eed36b055242c0ac30000d533`	https://huggingface.co/marduk191/rife (mirror of Practical-RIFE rife49; upstream MIT https://github.com/hzwer/Practical-RIFE)
`svi/SVI_Wan2.2-I2V-A14B_high_noise_lora_v2.0_pro.safetensors`	1226928552	`299b33006863194d077a43bc0abf16fc52963457657d867763f2b61fd6a9bd52`	https://huggingface.co/vita-video-gen/svi-model/tree/main/version-2.0 (MIT)
`svi/SVI_Wan2.2-I2V-A14B_low_noise_lora_v2.0_pro.safetensors`	1226928552	`e8fcce153df0f5a2b49a17c2f82bd795002f0e3b35f25d6922da9cfe072b9c0b`	https://huggingface.co/vita-video-gen/svi-model/tree/main/version-2.0 (MIT)
`t2v/Wan2_1-T2V-14B_fp8_e4m3fn.safetensors`	14859762840	`3dfae01b9fb11a95bc9ec13eea15399fa88fe05f8f4d95a71fe796693a2741d2`	https://huggingface.co/Kijai/WanVideo_comfy (Wan2.1 T2V 14B, upstream Wan-AI/Wan2.1-T2V-14B Apache-2.0)
`text_encoders/umt5-xxl-enc-fp8_e4m3fn.safetensors`	6731333792	`3fe5173588270c22505d4f9158bb1644b78331b8614206a97e92760b960c9ffa`	https://huggingface.co/Kijai/WanVideo_comfy (umt5-xxl, upstream google/umt5-xxl Apache-2.0)
`upscale/RealESRGAN_x2plus.pth`	67061725	`49fafd45f8fd7aa8d31ab2a22d14d91b536c34494a5cfe31eb5d89c2fa266abb`	https://github.com/xinntao/Real-ESRGAN/releases (BSD-3-Clause)
`upscale/RealESRGAN_x4plus.pth`	67040989	`4fa0d38905f75ac06eb49a7951b426670021be3018265fd191d2125df9d682f1`	https://github.com/xinntao/Real-ESRGAN/releases (BSD-3-Clause)
`vace/Wan2_1-VACE_module_14B_fp8_e4m3fn.safetensors`	3052113849	`4e251417a499fcdce54b6cddbd53d85644bcafb4e3d43a7d10c346612cb75501`	https://huggingface.co/Kijai/WanVideo_comfy (Wan2.1 VACE, upstream Wan-AI/Wan2.1-VACE-14B Apache-2.0)
`vae/Wan2_1_VAE_bf16.safetensors`	253806278	`1ab9a32cc2c740f6e39d80d367ce5dcc28db8c71b79b28670546b8973e9d75f9`	https://huggingface.co/Kijai/WanVideo_comfy (Wan2.1 VAE, upstream Wan-AI/Wan2.1-T2V-14B Apache-2.0)

Licenses and attribution

Each file keeps the license of its upstream model (see table). All permit redistribution: Apache-2.0 (Wan-AI Wan2.1 family, umt5-xxl, lightx2v distill LoRA), MIT (SVI 2.0 Pro LoRAs by vita-video-gen; RIFE by hzwer, Practical-RIFE), BSD-3-Clause (Real-ESRGAN by xinntao). Copies of the upstream license texts apply; see the linked sources. Weights are not modified except the renamed lightx2v file.

Downloads last month: -

GGUF

Model size

8B params

Architecture

lfm2moe

Hardware compatibility

4-bit

Inference Providers NEW

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