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

Libraries

How to use skymizer/quantized-debug-models with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="skymizer/quantized-debug-models",
	filename="deepseek-r1-distill-qwen-1.5b-q3_k_m-b10.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 skymizer/quantized-debug-models with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf skymizer/quantized-debug-models:Q3_K_M
# Run inference directly in the terminal:
llama-cli -hf skymizer/quantized-debug-models:Q3_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf skymizer/quantized-debug-models:Q3_K_M
# Run inference directly in the terminal:
llama-cli -hf skymizer/quantized-debug-models:Q3_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 skymizer/quantized-debug-models:Q3_K_M
# Run inference directly in the terminal:
./llama-cli -hf skymizer/quantized-debug-models:Q3_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 skymizer/quantized-debug-models:Q3_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf skymizer/quantized-debug-models:Q3_K_M

Use Docker

docker model run hf.co/skymizer/quantized-debug-models:Q3_K_M

LM Studio
Jan
Ollama
How to use skymizer/quantized-debug-models with Ollama:
```
ollama run hf.co/skymizer/quantized-debug-models:Q3_K_M
```

Unsloth Studio new

How to use skymizer/quantized-debug-models 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 skymizer/quantized-debug-models 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 skymizer/quantized-debug-models to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for skymizer/quantized-debug-models to start chatting

Docker Model Runner
How to use skymizer/quantized-debug-models with Docker Model Runner:
```
docker model run hf.co/skymizer/quantized-debug-models:Q3_K_M
```

Lemonade

How to use skymizer/quantized-debug-models with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull skymizer/quantized-debug-models:Q3_K_M

Run and chat with the model

lemonade run user.quantized-debug-models-Q3_K_M

List all available models

lemonade list

elichen-skymizer commited on Oct 27, 2025

Commit

8c0425b

1 Parent(s): bb2e298

Upload qwen3-4b-thinking-2507-q4_k_m-dc-b10-requant-all-k2000.gguf with huggingface_hub

Browse files

Files changed (1) hide show

.gitattributes +1 -0

.gitattributes CHANGED Viewed

@@ -66,3 +66,4 @@ qwen3-4b-thinking-2507-q3_k_m-dc-b10-debug-200.gguf filter=lfs diff=lfs merge=lf
 qwen3-4b-thinking-2507-q4_k_m-dc-b10-debug-2000.gguf filter=lfs diff=lfs merge=lfs -text
 qwen3-4b-thinking-2507-q3_k_m-dc-b10-debug-2000.gguf filter=lfs diff=lfs merge=lfs -text
 qwen3-4b-thinking-2507-q3_k_m-dc-b10-requant-all-k2000.gguf filter=lfs diff=lfs merge=lfs -text

 qwen3-4b-thinking-2507-q4_k_m-dc-b10-debug-2000.gguf filter=lfs diff=lfs merge=lfs -text
 qwen3-4b-thinking-2507-q3_k_m-dc-b10-debug-2000.gguf filter=lfs diff=lfs merge=lfs -text
 qwen3-4b-thinking-2507-q3_k_m-dc-b10-requant-all-k2000.gguf filter=lfs diff=lfs merge=lfs -text
+qwen3-4b-thinking-2507-q4_k_m-dc-b10-requant-all-k2000.gguf filter=lfs diff=lfs merge=lfs -text