Instructions to use rohits98/smollm360-ollama-test with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use rohits98/smollm360-ollama-test with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="rohits98/smollm360-ollama-test",
	filename="smollm360.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use rohits98/smollm360-ollama-test with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf rohits98/smollm360-ollama-test
# Run inference directly in the terminal:
llama-cli -hf rohits98/smollm360-ollama-test

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf rohits98/smollm360-ollama-test
# Run inference directly in the terminal:
llama-cli -hf rohits98/smollm360-ollama-test

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 rohits98/smollm360-ollama-test
# Run inference directly in the terminal:
./llama-cli -hf rohits98/smollm360-ollama-test

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 rohits98/smollm360-ollama-test
# Run inference directly in the terminal:
./build/bin/llama-cli -hf rohits98/smollm360-ollama-test

Use Docker

docker model run hf.co/rohits98/smollm360-ollama-test

LM Studio
Jan
Ollama
How to use rohits98/smollm360-ollama-test with Ollama:
```
ollama run hf.co/rohits98/smollm360-ollama-test
```

Unsloth Studio

How to use rohits98/smollm360-ollama-test 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 rohits98/smollm360-ollama-test 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 rohits98/smollm360-ollama-test to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for rohits98/smollm360-ollama-test to start chatting

Docker Model Runner
How to use rohits98/smollm360-ollama-test with Docker Model Runner:
```
docker model run hf.co/rohits98/smollm360-ollama-test
```

Lemonade

How to use rohits98/smollm360-ollama-test with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull rohits98/smollm360-ollama-test

Run and chat with the model

lemonade run user.smollm360-ollama-test-{{QUANT_TAG}}

List all available models

lemonade list

SmolLM-360M GGUF

This is a GGUF conversion of HuggingFaceTB/SmolLM-360M, generated using llama.cpp's convert_hf_to_gguf.py.

Files

smollm360.gguf – FP16 GGUF weights
smollm360.Q4_K_M.gguf – Quantized GGUF weights (optional)
config.json – Model architecture metadata
Tokenizer files – copied from the original repo

Usage with Ollama

Create a Modelfile:

FROM ./smollm360.gguf
PARAMETER temperature 0.1
SYSTEM "You are a helpful assistant. Answer questions directly and clearly."

Then run

ollama create smollm360 -f modelfile

and finally

ollama run smollm360

Downloads last month: 37

GGUF

Model size

0.4B params

Architecture

llama

Hardware compatibility

We're not able to determine the quantization variants.

View all variants

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for rohits98/smollm360-ollama-test

Base model

HuggingFaceTB/SmolLM3-3B-Base

Finetuned

HuggingFaceTB/SmolLM3-3B

Quantized

(87)

this model