Instructions to use mradermacher/Stentor-30M-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mradermacher/Stentor-30M-GGUF with Transformers:

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

pipe = pipeline("text-generation", model="mradermacher/Stentor-30M-GGUF")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("mradermacher/Stentor-30M-GGUF", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use mradermacher/Stentor-30M-GGUF with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf mradermacher/Stentor-30M-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf mradermacher/Stentor-30M-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf mradermacher/Stentor-30M-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf mradermacher/Stentor-30M-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/Stentor-30M-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf mradermacher/Stentor-30M-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/Stentor-30M-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf mradermacher/Stentor-30M-GGUF:Q4_K_M

Use Docker

docker model run hf.co/mradermacher/Stentor-30M-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use mradermacher/Stentor-30M-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "mradermacher/Stentor-30M-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": "mradermacher/Stentor-30M-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/mradermacher/Stentor-30M-GGUF:Q4_K_M

SGLang

How to use mradermacher/Stentor-30M-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 "mradermacher/Stentor-30M-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": "mradermacher/Stentor-30M-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 "mradermacher/Stentor-30M-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": "mradermacher/Stentor-30M-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use mradermacher/Stentor-30M-GGUF with Ollama:
```
ollama run hf.co/mradermacher/Stentor-30M-GGUF:Q4_K_M
```

Unsloth Studio

How to use mradermacher/Stentor-30M-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/Stentor-30M-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/Stentor-30M-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/Stentor-30M-GGUF to start chatting

How to use mradermacher/Stentor-30M-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf mradermacher/Stentor-30M-GGUF:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/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/Stentor-30M-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use mradermacher/Stentor-30M-GGUF with Docker Model Runner:
```
docker model run hf.co/mradermacher/Stentor-30M-GGUF:Q4_K_M
```

Lemonade

How to use mradermacher/Stentor-30M-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull mradermacher/Stentor-30M-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Stentor-30M-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use mradermacher/Stentor-30M-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf mradermacher/Stentor-30M-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/Stentor-30M-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use mradermacher/Stentor-30M-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf mradermacher/Stentor-30M-GGUF:Q4_K_M

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "mradermacher/Stentor-30M-GGUF:Q4_K_M" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

mradermacher commited on Feb 20

Commit

a9c0942

verified ·

1 Parent(s): 317d805

auto-patch README.md

Browse files

Files changed (1) hide show

README.md +84 -0

README.md CHANGED Viewed

@@ -1,3 +1,36 @@
 <!-- ### quantize_version: 2 -->
 <!-- ### output_tensor_quantised: 1 -->
 <!-- ### convert_type: hf -->
@@ -7,3 +40,54 @@
 <!-- ### quants_skip:  -->
 <!-- ### skip_mmproj:  -->
 static quants of https://huggingface.co/StentorLabs/Stentor-30M

+---
+base_model: StentorLabs/Stentor-30M
+datasets:
+- HuggingFaceFW/fineweb-edu
+- HuggingFaceTB/smollm-corpus
+language:
+- en
+library_name: transformers
+license: apache-2.0
+mradermacher:
+  readme_rev: 1
+quantized_by: mradermacher
+tags:
+- text-generation
+- llama
+- small-language-model
+- efficient
+- edge-deployment
+- speculative-decoding
+- tiny-model
+- 30m-parameters
+- kaggle-trained
+- educational
+- research
+- low-resource
+- cpu-inference
+- mobile-deployment
+- synthetic-data
+- fineweb
+- cosmopedia
+---
+## About
 <!-- ### quantize_version: 2 -->
 <!-- ### output_tensor_quantised: 1 -->
 <!-- ### convert_type: hf -->
 <!-- ### quants_skip:  -->
 <!-- ### skip_mmproj:  -->
 static quants of https://huggingface.co/StentorLabs/Stentor-30M
+<!-- provided-files -->
+***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Stentor-30M-GGUF).***
+weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion.
+## Usage
+If you are unsure how to use GGUF files, refer to one of [TheBloke's
+READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
+more details, including on how to concatenate multi-part files.
+## Provided Quants
+(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
+| Link | Type | Size/GB | Notes |
+|:-----|:-----|--------:|:------|
+| [GGUF](https://huggingface.co/mradermacher/Stentor-30M-GGUF/resolve/main/Stentor-30M.Q2_K.gguf) | Q2_K | 0.1 |  |
+| [GGUF](https://huggingface.co/mradermacher/Stentor-30M-GGUF/resolve/main/Stentor-30M.Q3_K_S.gguf) | Q3_K_S | 0.1 |  |
+| [GGUF](https://huggingface.co/mradermacher/Stentor-30M-GGUF/resolve/main/Stentor-30M.Q3_K_M.gguf) | Q3_K_M | 0.1 | lower quality |
+| [GGUF](https://huggingface.co/mradermacher/Stentor-30M-GGUF/resolve/main/Stentor-30M.Q3_K_L.gguf) | Q3_K_L | 0.1 |  |
+| [GGUF](https://huggingface.co/mradermacher/Stentor-30M-GGUF/resolve/main/Stentor-30M.IQ4_XS.gguf) | IQ4_XS | 0.1 |  |
+| [GGUF](https://huggingface.co/mradermacher/Stentor-30M-GGUF/resolve/main/Stentor-30M.Q4_K_S.gguf) | Q4_K_S | 0.1 | fast, recommended |
+| [GGUF](https://huggingface.co/mradermacher/Stentor-30M-GGUF/resolve/main/Stentor-30M.Q4_K_M.gguf) | Q4_K_M | 0.1 | fast, recommended |
+| [GGUF](https://huggingface.co/mradermacher/Stentor-30M-GGUF/resolve/main/Stentor-30M.Q5_K_S.gguf) | Q5_K_S | 0.1 |  |
+| [GGUF](https://huggingface.co/mradermacher/Stentor-30M-GGUF/resolve/main/Stentor-30M.Q5_K_M.gguf) | Q5_K_M | 0.1 |  |
+| [GGUF](https://huggingface.co/mradermacher/Stentor-30M-GGUF/resolve/main/Stentor-30M.Q6_K.gguf) | Q6_K | 0.1 | very good quality |
+| [GGUF](https://huggingface.co/mradermacher/Stentor-30M-GGUF/resolve/main/Stentor-30M.Q8_0.gguf) | Q8_0 | 0.1 | fast, best quality |
+| [GGUF](https://huggingface.co/mradermacher/Stentor-30M-GGUF/resolve/main/Stentor-30M.f16.gguf) | f16 | 0.2 | 16 bpw, overkill |
+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)
+And here are Artefact2's thoughts on the matter:
+https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
+## FAQ / Model Request
+See https://huggingface.co/mradermacher/model_requests for some answers to
+questions you might have and/or if you want some other model quantized.
+## Thanks
+I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
+me use its servers and providing upgrades to my workstation to enable
+this work in my free time.
+<!-- end -->