Instructions to use mradermacher/Draco-CoderMini-3B-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mradermacher/Draco-CoderMini-3B-GGUF with Transformers:

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("mradermacher/Draco-CoderMini-3B-GGUF", dtype="auto")

llama-cpp-python

How to use mradermacher/Draco-CoderMini-3B-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="mradermacher/Draco-CoderMini-3B-GGUF",
	filename="Draco-CoderMini-3B.IQ4_XS.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use mradermacher/Draco-CoderMini-3B-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf mradermacher/Draco-CoderMini-3B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf mradermacher/Draco-CoderMini-3B-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf mradermacher/Draco-CoderMini-3B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf mradermacher/Draco-CoderMini-3B-GGUF:Q4_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 mradermacher/Draco-CoderMini-3B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf mradermacher/Draco-CoderMini-3B-GGUF:Q4_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 mradermacher/Draco-CoderMini-3B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf mradermacher/Draco-CoderMini-3B-GGUF:Q4_K_M

Use Docker

docker model run hf.co/mradermacher/Draco-CoderMini-3B-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use mradermacher/Draco-CoderMini-3B-GGUF with Ollama:
```
ollama run hf.co/mradermacher/Draco-CoderMini-3B-GGUF:Q4_K_M
```

Unsloth Studio

How to use mradermacher/Draco-CoderMini-3B-GGUF 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 mradermacher/Draco-CoderMini-3B-GGUF 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 mradermacher/Draco-CoderMini-3B-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for mradermacher/Draco-CoderMini-3B-GGUF to start chatting

Docker Model Runner
How to use mradermacher/Draco-CoderMini-3B-GGUF with Docker Model Runner:
```
docker model run hf.co/mradermacher/Draco-CoderMini-3B-GGUF:Q4_K_M
```

Lemonade

How to use mradermacher/Draco-CoderMini-3B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull mradermacher/Draco-CoderMini-3B-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Draco-CoderMini-3B-GGUF-Q4_K_M

List all available models

lemonade list

mradermacher commited on May 27, 2025

Commit

6cf7add

verified ·

1 Parent(s): 0301b32

uploaded from back

Browse files

Files changed (13) hide show

.gitattributes +12 -0
Draco-CoderMini-3B.IQ4_XS.gguf +3 -0
Draco-CoderMini-3B.Q2_K.gguf +3 -0
Draco-CoderMini-3B.Q3_K_L.gguf +3 -0
Draco-CoderMini-3B.Q3_K_M.gguf +3 -0
Draco-CoderMini-3B.Q3_K_S.gguf +3 -0
Draco-CoderMini-3B.Q4_K_M.gguf +3 -0
Draco-CoderMini-3B.Q4_K_S.gguf +3 -0
Draco-CoderMini-3B.Q5_K_M.gguf +3 -0
Draco-CoderMini-3B.Q5_K_S.gguf +3 -0
Draco-CoderMini-3B.Q6_K.gguf +3 -0
Draco-CoderMini-3B.Q8_0.gguf +3 -0
Draco-CoderMini-3B.f16.gguf +3 -0

@@ -33,3 +33,15 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text

 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+Draco-CoderMini-3B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
+Draco-CoderMini-3B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+Draco-CoderMini-3B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+Draco-CoderMini-3B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Draco-CoderMini-3B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Draco-CoderMini-3B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Draco-CoderMini-3B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Draco-CoderMini-3B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Draco-CoderMini-3B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Draco-CoderMini-3B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+Draco-CoderMini-3B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+Draco-CoderMini-3B.f16.gguf filter=lfs diff=lfs merge=lfs -text

+version https://git-lfs.github.com/spec/v1
+oid sha256:6f96f0c2440ecfc85c2aa1c662c23642ef037cf9841c5eaa4900564d2fbcbcec
+size 1753182976

+version https://git-lfs.github.com/spec/v1
+oid sha256:66e7d1e63bcb05229582f0624a82206573a5c80f02afd231fe61645e42d0bf60
+size 1274753792

+version https://git-lfs.github.com/spec/v1
+oid sha256:8fdad34a8789dfdfe9794d72bc8dd1605017ccfece1da1d6e699ef0eb6df0f7b
+size 1707389696

+version https://git-lfs.github.com/spec/v1
+oid sha256:2a8c0faf526016f2140dbe8571f903421178a569c7ee100fa0028953c7460e84
+size 1590473472

+version https://git-lfs.github.com/spec/v1
+oid sha256:5b06626dce17507770340a5091bd7686873e5f4622dd7f7daf29883f2f47d277
+size 1454355200

+version https://git-lfs.github.com/spec/v1
+oid sha256:9d0f5a21a14e05ff28b106c4a9b57119a92599d169c2cfb3fa9b1e78ee6f2721
+size 1929900800

+version https://git-lfs.github.com/spec/v1
+oid sha256:81923dfa97cddcda0a274a54c415db427d7b649c7ae974c1178c42889105190f
+size 1834382080

+version https://git-lfs.github.com/spec/v1
+oid sha256:40c806a64d953471c14f5fbb700bd2c4196f0badeed31c179a4ce7f4f83c9677
+size 2224812800

+version https://git-lfs.github.com/spec/v1
+oid sha256:4732318d13392cd9a5df632c1009cd35a7f01feb6cb7b982db01ec1a34e815bb
+size 2169664256

+version https://git-lfs.github.com/spec/v1
+oid sha256:98ea826de53ad001acde646594ca6fc61554a1ef01d180b39bc830a794f3a904
+size 2538156800

	@@ -0,0 +1,3 @@

	@@ -0,0 +1,3 @@

	@@ -0,0 +1,3 @@

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:176b2f68068253d460c2e4f4e701971b64b12692f61a8c535881c339b453f9ab
+size 3285474048

+version https://git-lfs.github.com/spec/v1
+oid sha256:1ecd571fce93c6b9ad24a6fa1e24ad849312dde6edf2e3a6c6e412815e39cb55
+size 6178315008