Instructions to use agentlans/SmolLM2-135M-Instruct-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use agentlans/SmolLM2-135M-Instruct-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="agentlans/SmolLM2-135M-Instruct-GGUF",
	filename="Q4_K_M.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use agentlans/SmolLM2-135M-Instruct-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf agentlans/SmolLM2-135M-Instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf agentlans/SmolLM2-135M-Instruct-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 agentlans/SmolLM2-135M-Instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf agentlans/SmolLM2-135M-Instruct-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 agentlans/SmolLM2-135M-Instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf agentlans/SmolLM2-135M-Instruct-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 agentlans/SmolLM2-135M-Instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf agentlans/SmolLM2-135M-Instruct-GGUF:Q4_K_M

Use Docker

docker model run hf.co/agentlans/SmolLM2-135M-Instruct-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use agentlans/SmolLM2-135M-Instruct-GGUF with Ollama:
```
ollama run hf.co/agentlans/SmolLM2-135M-Instruct-GGUF:Q4_K_M
```

Unsloth Studio new

How to use agentlans/SmolLM2-135M-Instruct-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 agentlans/SmolLM2-135M-Instruct-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 agentlans/SmolLM2-135M-Instruct-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for agentlans/SmolLM2-135M-Instruct-GGUF to start chatting

Docker Model Runner
How to use agentlans/SmolLM2-135M-Instruct-GGUF with Docker Model Runner:
```
docker model run hf.co/agentlans/SmolLM2-135M-Instruct-GGUF:Q4_K_M
```

Lemonade

How to use agentlans/SmolLM2-135M-Instruct-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull agentlans/SmolLM2-135M-Instruct-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.SmolLM2-135M-Instruct-GGUF-Q4_K_M

List all available models

lemonade list

SmolLM2 135M Quantized Models

This repo offers quantized versions of the HuggingFaceTB/SmolLM2-135M-Instruct model, optimized for llama.cpp with Q4_K_M, Q5_K_M, and Q8_0 quantizations. These were built using an unofficial Docker image.

Calibration

Models were calibrated on 1000 samples from the openbmb/Ultra-FineWeb dataset to maintain coherent output. The resulting imatrix.dat file is included.

Example Interaction

With the Q4_K_M quantized model

User: What is AI?
Reply: AI is an intelligent and sophisticated system that processes and analyzes vast amounts of data to learn, understand, and perform tasks. It is a branch of computer science that focuses on enabling machines to perform tasks that typically require human intelligence, such as learning, reasoning, and problem-solving. AI is often associated with machines that can reason, learn, and improve their performance over time, allowing them to recognize patterns, make decisions, and adapt to new situations. AI has applications across various fields, including technology, business, healthcare, and education. It is considered to be one of the most promising fields in the field of artificial intelligence and machine learning, as it can automate a wide range of tasks and provide new insights and discoveries in many areas of life and work.

Performance

Very fast. On an NVIDIA RTX 4070, the Q4 model can generate close to 300 tokens per second.

Limitations

Same constraints as the original small SmolLM2-135M-Instruct model
Not ideal for complex tasks
Mainly suited for language generation and experimentation

Downloads last month: 61

GGUF

Model size

0.1B params

Architecture

llama

Hardware compatibility

4-bit

5-bit

8-bit

Inference Providers NEW

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

Model tree for agentlans/SmolLM2-135M-Instruct-GGUF

Base model

HuggingFaceTB/SmolLM2-135M

Quantized

HuggingFaceTB/SmolLM2-135M-Instruct

Quantized

(99)

this model

agentlans
/

SmolLM2-135M-Instruct-GGUF