Text Generation
GGUF
English
agentic
agent
tool-use
function-calling
code
terminal
swe
qwen3.5
small-models
edge
llama.cpp
ollama
conversational
Instructions to use Hob-forge/smeagle-4b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use Hob-forge/smeagle-4b 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 Hob-forge/smeagle-4b:Q4_K_M # Run inference directly in the terminal: llama cli -hf Hob-forge/smeagle-4b:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf Hob-forge/smeagle-4b:Q4_K_M # Run inference directly in the terminal: llama cli -hf Hob-forge/smeagle-4b: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 Hob-forge/smeagle-4b:Q4_K_M # Run inference directly in the terminal: ./llama-cli -hf Hob-forge/smeagle-4b: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 Hob-forge/smeagle-4b:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama-cli -hf Hob-forge/smeagle-4b:Q4_K_M
Use Docker
docker model run hf.co/Hob-forge/smeagle-4b:Q4_K_M
- LM Studio
- Jan
- vLLM
How to use Hob-forge/smeagle-4b with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Hob-forge/smeagle-4b" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Hob-forge/smeagle-4b", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/Hob-forge/smeagle-4b:Q4_K_M
- Ollama
How to use Hob-forge/smeagle-4b with Ollama:
ollama run hf.co/Hob-forge/smeagle-4b:Q4_K_M
- Unsloth Studio
How to use Hob-forge/smeagle-4b 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 Hob-forge/smeagle-4b 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 Hob-forge/smeagle-4b to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for Hob-forge/smeagle-4b to start chatting
- Pi
How to use Hob-forge/smeagle-4b with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf Hob-forge/smeagle-4b: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": "Hob-forge/smeagle-4b:Q4_K_M" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Docker Model Runner
How to use Hob-forge/smeagle-4b with Docker Model Runner:
docker model run hf.co/Hob-forge/smeagle-4b:Q4_K_M
- Lemonade
How to use Hob-forge/smeagle-4b with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull Hob-forge/smeagle-4b:Q4_K_M
Run and chat with the model
lemonade run user.smeagle-4b-Q4_K_M
List all available models
lemonade list
- Hermes Agent
How to use Hob-forge/smeagle-4b with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf Hob-forge/smeagle-4b: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 Hob-forge/smeagle-4b:Q4_K_M
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use Hob-forge/smeagle-4b with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf Hob-forge/smeagle-4b: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 "Hob-forge/smeagle-4b: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"
Add Hob Forge Community License v1.0 (billboard clause for 10M+/frontier users)
Browse files- LICENSE.md +40 -0
LICENSE.md
ADDED
|
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Hob Forge Community License — smeagle v1.0
|
| 2 |
+
|
| 3 |
+
smeagle is a fine-tune of **Qwen/Qwen3.5-4B-Base** (© Alibaba, Apache-2.0). The base model remains under
|
| 4 |
+
Apache-2.0 and nothing here limits your Apache-2.0 rights to it. This license governs **Hob Forge's
|
| 5 |
+
fine-tuning contribution** — the smeagle weights, GGUFs, and derivatives of them.
|
| 6 |
+
|
| 7 |
+
Plain-English summary (the terms below control if there's ever a conflict): **free for almost everyone,
|
| 8 |
+
attribution always, and if you're a giant you have to say you use it.**
|
| 9 |
+
|
| 10 |
+
## 1. Grant — free for almost everyone
|
| 11 |
+
You may use, run, modify, quantize, distribute, and build on smeagle — commercially or not, at no cost —
|
| 12 |
+
subject to the terms below. If you're an individual, a hobbyist, a startup, a research group, a school, or
|
| 13 |
+
a small-to-mid-size company: this is yours. Run it on your laptop and ship products with it, freely.
|
| 14 |
+
|
| 15 |
+
## 2. Attribution — always
|
| 16 |
+
When you distribute smeagle or a derivative of it, keep a visible credit to
|
| 17 |
+
**"Hob Forge — smeagle (https://huggingface.co/Hob-forge/smeagle-4b)"** in your model card, README, docs,
|
| 18 |
+
or about page.
|
| 19 |
+
|
| 20 |
+
## 3. The billboard clause — large-scale users must disclose
|
| 21 |
+
If you are **(a)** a frontier AI lab, **or (b)** any organisation serving smeagle or a derivative of it to
|
| 22 |
+
more than **10,000,000 (ten million) monthly active users**, then in ADDITION to §2 you must **prominently
|
| 23 |
+
and publicly disclose** that your product uses a Hob Forge fine-tune (smeagle), somewhere your users can
|
| 24 |
+
see it (e.g. product/model documentation, a model list, or an about page). If smeagle helps you serve
|
| 25 |
+
millions, say so out loud. That's the price of scale.
|
| 26 |
+
|
| 27 |
+
## 4. Guardrails — non-negotiable
|
| 28 |
+
- **Do not** use smeagle to produce material that sexualizes, exploits, or endangers children. Absolute.
|
| 29 |
+
- **Do not** strip or defeat safety alignment ("abliterate") and then redistribute it as a Hob Forge model.
|
| 30 |
+
- **Do not** present smeagle's output as human-authored in a way meant to deceive or harm.
|
| 31 |
+
|
| 32 |
+
## 5. No warranty
|
| 33 |
+
Provided "AS IS", without warranty of any kind. Hob Forge is not liable for how you use it.
|
| 34 |
+
|
| 35 |
+
## 6. Base model
|
| 36 |
+
Qwen3.5-4B-Base © Alibaba Cloud, licensed Apache-2.0. Its terms are preserved and unaffected by this license.
|
| 37 |
+
|
| 38 |
+
---
|
| 39 |
+
*Hob Forge is a small sovereign AI lab. This is a plain-language community license; for large-scale
|
| 40 |
+
commercial reliance you should have your own counsel review it. Questions: huggingface.co/Hob-forge.*
|