Instructions to use rootxhacker/HobbyLM-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use rootxhacker/HobbyLM-gguf with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="rootxhacker/HobbyLM-gguf",
	filename="HobbyLM-Base.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 rootxhacker/HobbyLM-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 rootxhacker/HobbyLM-gguf
# Run inference directly in the terminal:
llama cli -hf rootxhacker/HobbyLM-gguf

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf rootxhacker/HobbyLM-gguf
# Run inference directly in the terminal:
llama cli -hf rootxhacker/HobbyLM-gguf

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 rootxhacker/HobbyLM-gguf
# Run inference directly in the terminal:
./llama-cli -hf rootxhacker/HobbyLM-gguf

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 rootxhacker/HobbyLM-gguf
# Run inference directly in the terminal:
./build/bin/llama-cli -hf rootxhacker/HobbyLM-gguf

Use Docker

docker model run hf.co/rootxhacker/HobbyLM-gguf

LM Studio
Jan
Ollama
How to use rootxhacker/HobbyLM-gguf with Ollama:
```
ollama run hf.co/rootxhacker/HobbyLM-gguf
```

Unsloth Studio

How to use rootxhacker/HobbyLM-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 rootxhacker/HobbyLM-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 rootxhacker/HobbyLM-gguf to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for rootxhacker/HobbyLM-gguf to start chatting

Atomic Chat new
Docker Model Runner
How to use rootxhacker/HobbyLM-gguf with Docker Model Runner:
```
docker model run hf.co/rootxhacker/HobbyLM-gguf
```

Lemonade

How to use rootxhacker/HobbyLM-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull rootxhacker/HobbyLM-gguf

Run and chat with the model

lemonade run user.HobbyLM-gguf-{{QUANT_TAG}}

List all available models

lemonade list

HobbyLM-gguf / README.md

rootxhacker

Upload README.md with huggingface_hub

3e1f920 verified 20 days ago

preview code

Raw

History Blame Contribute Delete

1.94 kB

	---
	license: apache-2.0
	tags: [hobbylm, gguf, mixture-of-experts, moe]
	---

	# HobbyLM-GGUF

	GGUF builds of every HobbyLM language model — one file per variant, all sharing the same 500M sparse-MoE
	core. These are the files you actually run on a laptop CPU.

	\| File \| Model \| What it's for \| Headline number \|
	\|---\|---\|---\|---\|
	\| `HobbyLM-Base.gguf` \| [Base](https://huggingface.co/rootxhacker/HobbyLM-Base) \| pretrained foundation LM \| 44.05 avg (0-shot, our harness) \|
	\| `HobbyLM-Chat.gguf` \| [Chat](https://huggingface.co/rootxhacker/HobbyLM-Chat) \| instruction / chat \| 42.5 avg (alignment-tax dip from base) \|
	\| `HobbyLM-Computer-Use.gguf` \| [Computer-Use](https://huggingface.co/rootxhacker/HobbyLM-Computer-Use) \| GUI agent + tool calling \| 95% name-F1, 0% param-hallucination \|
	\| `HobbyLM-Omni.gguf` \| [Omni](https://huggingface.co/rootxhacker/HobbyLM-Omni) \| multimodal core (text+image+audio) \| VQAv2 47.0 / GQA 39.2 \|
	\| `HobbyLM-Diffusion.gguf` \| [Diffusion](https://huggingface.co/rootxhacker/HobbyLM-Diffusion) \| masked-diffusion LM \| 117 tok/s on H100 (~2.7× AR) \|

	Full benchmark tables, methodology, and limitations are on each model's own card (linked above).

	## Running them

	```bash
	# from https://github.com/harishsg993010/HobbyLM
	hobby-rs --model HobbyLM-Chat.gguf --prompt "The capital of France is" --n 48
	```

	## ⚠️ These use a custom `hobbylm` architecture

	Every GGUF sets `general.architecture = hobbylm` (all metadata keys are `hobbylm.`). *Stock llama.cpp will
	not load them** — they need the from-scratch [`hobby-rs`](https://github.com/harishsg993010/HobbyLM) engine,
	or a llama.cpp patched to register the `hobbylm` arch (GQA + per-head QK-norm + sigmoid-gated MoE + aux-free
	routing bias + 1 shared expert + a leading dense layer). `HobbyLM-Diffusion` additionally carries `diffusion.*`
	metadata and needs the diffusion-aware (bidirectional, iterative-denoise) decoder.

	## License
	Apache-2.0.