Instructions to use MidnightRunner/Misc with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use MidnightRunner/Misc with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="MidnightRunner/Misc",
	filename="Qwen2.5-VL-7B-Instruct-Q3_K_S.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use MidnightRunner/Misc with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf MidnightRunner/Misc:UD-Q4_K_S
# Run inference directly in the terminal:
llama-cli -hf MidnightRunner/Misc:UD-Q4_K_S

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf MidnightRunner/Misc:UD-Q4_K_S
# Run inference directly in the terminal:
llama-cli -hf MidnightRunner/Misc:UD-Q4_K_S

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 MidnightRunner/Misc:UD-Q4_K_S
# Run inference directly in the terminal:
./llama-cli -hf MidnightRunner/Misc:UD-Q4_K_S

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 MidnightRunner/Misc:UD-Q4_K_S
# Run inference directly in the terminal:
./build/bin/llama-cli -hf MidnightRunner/Misc:UD-Q4_K_S

Use Docker

docker model run hf.co/MidnightRunner/Misc:UD-Q4_K_S

LM Studio
Jan
Ollama
How to use MidnightRunner/Misc with Ollama:
```
ollama run hf.co/MidnightRunner/Misc:UD-Q4_K_S
```

Unsloth Studio new

How to use MidnightRunner/Misc 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 MidnightRunner/Misc 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 MidnightRunner/Misc to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for MidnightRunner/Misc to start chatting

Docker Model Runner
How to use MidnightRunner/Misc with Docker Model Runner:
```
docker model run hf.co/MidnightRunner/Misc:UD-Q4_K_S
```

Lemonade

How to use MidnightRunner/Misc with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull MidnightRunner/Misc:UD-Q4_K_S

Run and chat with the model

lemonade run user.Misc-UD-Q4_K_S

List all available models

lemonade list

🗂 MidnightRunner/Misc

Overview

This repo is my miscellaneous toolbox — a collection of models, upscalers, denoisers, configs, and other bits I keep around for quick pulls.

It’s not meant to be polished, just fast standbys that I can drop into workflows when needed.

Upscalers
- ESRGAN, RealESRGAN, AnimeSharp, UltraSharp
- SwinIR, NMKD, Foolhardy
Denoisers & Sharpeners
- ITF SkinDiff Detail Lite
- Lexica Sharp series
- DeNoise realplksr
Experimental Checkpoints
- Astraali configs
- OmniSR (x2, x3, x4)
- SAM (Segment Anything) weights
- Motion tests (bounceV, danceMax, etc.)
Workflow Utilities
- FixFP16Errors
- Oddball safetensors
- “Just in case” helper models

Quick Pulls

Fetch files or the entire repo with Hugging Face tools:

# clone the whole repo
git lfs install
git clone https://huggingface.co/MidnightRunner/Misc

# download a single file
huggingface-cli download MidnightRunner/Misc 4x-UltraSharp.pth

# pull from Python
from huggingface_hub import hf_hub_download

file = hf_hub_download(
    repo_id="MidnightRunner/Misc",
    filename="4x-UltraSharp.pth"
)

Notes

Disorganized on purpose: this is a stash, not a showcase.
Everything here is tested, works, and has bailed me out more than once.
Licenses follow their original sources.

Downloads last month: 136

GGUF

Model size

8B params

Architecture

qwen2vl

Hardware compatibility

3-bit

4-bit

8-bit

Inference Providers NEW

Other

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

MidnightRunner
/

Misc

🗂 MidnightRunner/Misc

Overview

Contents

Quick Pulls

Notes