Instructions to use prithivMLmods/OpenScienceReasoning-Qwen-e10-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use prithivMLmods/OpenScienceReasoning-Qwen-e10-GGUF with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="prithivMLmods/OpenScienceReasoning-Qwen-e10-GGUF")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("prithivMLmods/OpenScienceReasoning-Qwen-e10-GGUF", dtype="auto")

llama-cpp-python

How to use prithivMLmods/OpenScienceReasoning-Qwen-e10-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="prithivMLmods/OpenScienceReasoning-Qwen-e10-GGUF",
	filename="OpenScienceReasoning-Qwen-e10.BF16.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use prithivMLmods/OpenScienceReasoning-Qwen-e10-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf prithivMLmods/OpenScienceReasoning-Qwen-e10-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf prithivMLmods/OpenScienceReasoning-Qwen-e10-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 prithivMLmods/OpenScienceReasoning-Qwen-e10-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf prithivMLmods/OpenScienceReasoning-Qwen-e10-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 prithivMLmods/OpenScienceReasoning-Qwen-e10-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf prithivMLmods/OpenScienceReasoning-Qwen-e10-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 prithivMLmods/OpenScienceReasoning-Qwen-e10-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf prithivMLmods/OpenScienceReasoning-Qwen-e10-GGUF:Q4_K_M

Use Docker

docker model run hf.co/prithivMLmods/OpenScienceReasoning-Qwen-e10-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use prithivMLmods/OpenScienceReasoning-Qwen-e10-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "prithivMLmods/OpenScienceReasoning-Qwen-e10-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "prithivMLmods/OpenScienceReasoning-Qwen-e10-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/prithivMLmods/OpenScienceReasoning-Qwen-e10-GGUF:Q4_K_M

SGLang

How to use prithivMLmods/OpenScienceReasoning-Qwen-e10-GGUF with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "prithivMLmods/OpenScienceReasoning-Qwen-e10-GGUF" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "prithivMLmods/OpenScienceReasoning-Qwen-e10-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "prithivMLmods/OpenScienceReasoning-Qwen-e10-GGUF" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "prithivMLmods/OpenScienceReasoning-Qwen-e10-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use prithivMLmods/OpenScienceReasoning-Qwen-e10-GGUF with Ollama:
```
ollama run hf.co/prithivMLmods/OpenScienceReasoning-Qwen-e10-GGUF:Q4_K_M
```

Unsloth Studio

How to use prithivMLmods/OpenScienceReasoning-Qwen-e10-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 prithivMLmods/OpenScienceReasoning-Qwen-e10-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 prithivMLmods/OpenScienceReasoning-Qwen-e10-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for prithivMLmods/OpenScienceReasoning-Qwen-e10-GGUF to start chatting

How to use prithivMLmods/OpenScienceReasoning-Qwen-e10-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf prithivMLmods/OpenScienceReasoning-Qwen-e10-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": "prithivMLmods/OpenScienceReasoning-Qwen-e10-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use prithivMLmods/OpenScienceReasoning-Qwen-e10-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 prithivMLmods/OpenScienceReasoning-Qwen-e10-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 prithivMLmods/OpenScienceReasoning-Qwen-e10-GGUF:Q4_K_M

Run Hermes

hermes

Docker Model Runner
How to use prithivMLmods/OpenScienceReasoning-Qwen-e10-GGUF with Docker Model Runner:
```
docker model run hf.co/prithivMLmods/OpenScienceReasoning-Qwen-e10-GGUF:Q4_K_M
```

Lemonade

How to use prithivMLmods/OpenScienceReasoning-Qwen-e10-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull prithivMLmods/OpenScienceReasoning-Qwen-e10-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.OpenScienceReasoning-Qwen-e10-GGUF-Q4_K_M

List all available models

lemonade list

prithivMLmods commited on Aug 31, 2025

Commit

0b1c42a

verified ·

1 Parent(s): a10fd3b

Update README.md

Browse files

Files changed (1) hide show

README.md +50 -3

README.md CHANGED Viewed

@@ -1,3 +1,50 @@
----
-license: apache-2.0
----

+---
+license: apache-2.0
+language:
+- en
+base_model:
+- prithivMLmods/OpenScienceReasoning-Qwen-e10
+pipeline_tag: text-generation
+library_name: transformers
+tags:
+- text-generation-inference
+- medical
+- science
+---
+# **OpenScienceReasoning-Qwen-e10-GGUF**
+> OpenScienceReasoning-Qwen-e10 is a high-efficiency scientific reasoning model fine-tuned from Qwen3-1.7B using the nvidia/OpenScienceReasoning-2 dataset, encompassing 10,000 curated science and math entries that strengthen analytical problem-solving, chain-of-thought exploration, and code reasoning. The model excels at hybrid symbolic-AI thinking by performing structured logic, scientific derivations, multi-language coding, and generating outputs in formats such as LaTeX, Markdown, JSON, CSV, and YAML, making it ideal for research, education, and technical documentation on mid-range GPUs and edge clusters. Optimized for STEM applications, OpenScienceReasoning-Qwen-e10 delivers robust performance for tutoring, research assistance, and structured data generation while maintaining a lightweight deployment footprint.
+## Model Files
+| File Name | Quant Type | File Size |
+| - | - | - |
+| OpenScienceReasoning-Qwen-e10.BF16.gguf | BF16 | 3.45 GB |
+| OpenScienceReasoning-Qwen-e10.F16.gguf | F16 | 3.45 GB |
+| OpenScienceReasoning-Qwen-e10.F32.gguf | F32 | 6.89 GB |
+| OpenScienceReasoning-Qwen-e10.Q2_K.gguf | Q2_K | 778 MB |
+| OpenScienceReasoning-Qwen-e10.Q3_K_L.gguf | Q3_K_L | 1 GB |
+| OpenScienceReasoning-Qwen-e10.Q3_K_M.gguf | Q3_K_M | 940 MB |
+| OpenScienceReasoning-Qwen-e10.Q3_K_S.gguf | Q3_K_S | 867 MB |
+| OpenScienceReasoning-Qwen-e10.Q4_0.gguf | Q4_0 | 1.05 GB |
+| OpenScienceReasoning-Qwen-e10.Q4_1.gguf | Q4_1 | 1.14 GB |
+| OpenScienceReasoning-Qwen-e10.Q4_K.gguf | Q4_K | 1.11 GB |
+| OpenScienceReasoning-Qwen-e10.Q4_K_M.gguf | Q4_K_M | 1.11 GB |
+| OpenScienceReasoning-Qwen-e10.Q4_K_S.gguf | Q4_K_S | 1.06 GB |
+| OpenScienceReasoning-Qwen-e10.Q5_0.gguf | Q5_0 | 1.23 GB |
+| OpenScienceReasoning-Qwen-e10.Q5_1.gguf | Q5_1 | 1.32 GB |
+| OpenScienceReasoning-Qwen-e10.Q5_K.gguf | Q5_K | 1.26 GB |
+| OpenScienceReasoning-Qwen-e10.Q5_K_M.gguf | Q5_K_M | 1.26 GB |
+| OpenScienceReasoning-Qwen-e10.Q5_K_S.gguf | Q5_K_S | 1.23 GB |
+| OpenScienceReasoning-Qwen-e10.Q6_K.gguf | Q6_K | 1.42 GB |
+| OpenScienceReasoning-Qwen-e10.Q8_0.gguf | Q8_0 | 1.83 GB |
+## Quants Usage
+(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
+Here is a handy graph by ikawrakow comparing some lower-quality quant
+types (lower is better):
+![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png)