Instructions to use mradermacher/Qwen2.5-1.5B-MegaScience-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mradermacher/Qwen2.5-1.5B-MegaScience-GGUF with Transformers:

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("mradermacher/Qwen2.5-1.5B-MegaScience-GGUF", dtype="auto")

llama-cpp-python

How to use mradermacher/Qwen2.5-1.5B-MegaScience-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="mradermacher/Qwen2.5-1.5B-MegaScience-GGUF",
	filename="Qwen2.5-1.5B-MegaScience.IQ4_XS.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use mradermacher/Qwen2.5-1.5B-MegaScience-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/Qwen2.5-1.5B-MegaScience-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf mradermacher/Qwen2.5-1.5B-MegaScience-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/Qwen2.5-1.5B-MegaScience-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf mradermacher/Qwen2.5-1.5B-MegaScience-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/Qwen2.5-1.5B-MegaScience-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf mradermacher/Qwen2.5-1.5B-MegaScience-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/Qwen2.5-1.5B-MegaScience-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf mradermacher/Qwen2.5-1.5B-MegaScience-GGUF:Q4_K_M

Use Docker

docker model run hf.co/mradermacher/Qwen2.5-1.5B-MegaScience-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use mradermacher/Qwen2.5-1.5B-MegaScience-GGUF with Ollama:
```
ollama run hf.co/mradermacher/Qwen2.5-1.5B-MegaScience-GGUF:Q4_K_M
```

Unsloth Studio

How to use mradermacher/Qwen2.5-1.5B-MegaScience-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/Qwen2.5-1.5B-MegaScience-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/Qwen2.5-1.5B-MegaScience-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/Qwen2.5-1.5B-MegaScience-GGUF to start chatting

How to use mradermacher/Qwen2.5-1.5B-MegaScience-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf mradermacher/Qwen2.5-1.5B-MegaScience-GGUF:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "mradermacher/Qwen2.5-1.5B-MegaScience-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use mradermacher/Qwen2.5-1.5B-MegaScience-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf mradermacher/Qwen2.5-1.5B-MegaScience-GGUF: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 mradermacher/Qwen2.5-1.5B-MegaScience-GGUF:Q4_K_M

Run Hermes

hermes

Docker Model Runner
How to use mradermacher/Qwen2.5-1.5B-MegaScience-GGUF with Docker Model Runner:
```
docker model run hf.co/mradermacher/Qwen2.5-1.5B-MegaScience-GGUF:Q4_K_M
```

Lemonade

How to use mradermacher/Qwen2.5-1.5B-MegaScience-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull mradermacher/Qwen2.5-1.5B-MegaScience-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Qwen2.5-1.5B-MegaScience-GGUF-Q4_K_M

List all available models

lemonade list

mradermacher commited on Jul 23, 2025

Commit

7f1daf2

verified ·

1 Parent(s): 665a2a7

uploaded from marco

Browse files

Files changed (13) hide show

.gitattributes +12 -0
Qwen2.5-1.5B-MegaScience.IQ4_XS.gguf +3 -0
Qwen2.5-1.5B-MegaScience.Q2_K.gguf +3 -0
Qwen2.5-1.5B-MegaScience.Q3_K_L.gguf +3 -0
Qwen2.5-1.5B-MegaScience.Q3_K_M.gguf +3 -0
Qwen2.5-1.5B-MegaScience.Q3_K_S.gguf +3 -0
Qwen2.5-1.5B-MegaScience.Q4_K_M.gguf +3 -0
Qwen2.5-1.5B-MegaScience.Q4_K_S.gguf +3 -0
Qwen2.5-1.5B-MegaScience.Q5_K_M.gguf +3 -0
Qwen2.5-1.5B-MegaScience.Q5_K_S.gguf +3 -0
Qwen2.5-1.5B-MegaScience.Q6_K.gguf +3 -0
Qwen2.5-1.5B-MegaScience.Q8_0.gguf +3 -0
Qwen2.5-1.5B-MegaScience.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
+Qwen2.5-1.5B-MegaScience.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-1.5B-MegaScience.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-1.5B-MegaScience.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-1.5B-MegaScience.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-1.5B-MegaScience.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-1.5B-MegaScience.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-1.5B-MegaScience.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-1.5B-MegaScience.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-1.5B-MegaScience.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-1.5B-MegaScience.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-1.5B-MegaScience.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-1.5B-MegaScience.f16.gguf filter=lfs diff=lfs merge=lfs -text

+version https://git-lfs.github.com/spec/v1
+oid sha256:e099a07cc56c26101b4b0542ef0e81923ad0fba1e60c56795ced413bf8d1acb6
+size 902183424

+version https://git-lfs.github.com/spec/v1
+oid sha256:c1595f948ba55eae78f556e52846a174e4f0c9d68abbc94dd07f788d3516d3e4
+size 676305408

+version https://git-lfs.github.com/spec/v1
+oid sha256:ea67e0e2f1ba2d7625d1398d733bacde35bde0db171f225650e9a482332007e4
+size 880163328

+version https://git-lfs.github.com/spec/v1
+oid sha256:55f5bc1eb96a3679d3680d24883a11cde460cd710089aea3f7947f91fba6a547
+size 824179200

+version https://git-lfs.github.com/spec/v1
+oid sha256:a2f7d43dbd114b29408c6fa2d97820fb1e16ba426104bf271313b7b20e6e38ff
+size 760945152

+version https://git-lfs.github.com/spec/v1
+oid sha256:cc438ea2f5de6788c157209e18853585604b8f429c3b94058d4be62b33322098
+size 986049024

+version https://git-lfs.github.com/spec/v1
+oid sha256:fcc575cf3fa22777f2743c54f1b053e4fed31ac412bbc42cf47f5f304d5ae893
+size 940313088

+version https://git-lfs.github.com/spec/v1
+oid sha256:f1bf8840d81fdeba5dc9d37bd2efe6f9d2cdaea80d750d9288bff92565776071
+size 1125050880

+version https://git-lfs.github.com/spec/v1
+oid sha256:762f90c021aaf3cbc76cc5b7ab744b01985e2379683b9aac5ee86fddcd5785b1
+size 1098729984

+version https://git-lfs.github.com/spec/v1
+oid sha256:87810dc5c62a1a76ee92359fc3ef4afe4196e7620693dd3c24af5bb7a3d000d8
+size 1272740352

	@@ -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 sha256:7b896c0e086a336a71b9cd68f03feea4b5c7143f187fa4d27cdb983adf4a531a
+size 1646573568

+version https://git-lfs.github.com/spec/v1
+oid sha256:5303faa1d6b0fcbb34f85de258f338d23e98e058832affdfa8114fd16f9f28ca
+size 3093669888