Instructions to use WJ1240424/SmolLM2-135M-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use WJ1240424/SmolLM2-135M-Instruct 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 WJ1240424/SmolLM2-135M-Instruct:F16
# Run inference directly in the terminal:
llama cli -hf WJ1240424/SmolLM2-135M-Instruct:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf WJ1240424/SmolLM2-135M-Instruct:F16
# Run inference directly in the terminal:
llama cli -hf WJ1240424/SmolLM2-135M-Instruct:F16

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 WJ1240424/SmolLM2-135M-Instruct:F16
# Run inference directly in the terminal:
./llama-cli -hf WJ1240424/SmolLM2-135M-Instruct:F16

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 WJ1240424/SmolLM2-135M-Instruct:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf WJ1240424/SmolLM2-135M-Instruct:F16

Use Docker

docker model run hf.co/WJ1240424/SmolLM2-135M-Instruct:F16

LM Studio
Jan
Ollama
How to use WJ1240424/SmolLM2-135M-Instruct with Ollama:
```
ollama run hf.co/WJ1240424/SmolLM2-135M-Instruct:F16
```

Unsloth Studio

How to use WJ1240424/SmolLM2-135M-Instruct 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 WJ1240424/SmolLM2-135M-Instruct 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 WJ1240424/SmolLM2-135M-Instruct to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for WJ1240424/SmolLM2-135M-Instruct to start chatting

Docker Model Runner
How to use WJ1240424/SmolLM2-135M-Instruct with Docker Model Runner:
```
docker model run hf.co/WJ1240424/SmolLM2-135M-Instruct:F16
```

Lemonade

How to use WJ1240424/SmolLM2-135M-Instruct with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull WJ1240424/SmolLM2-135M-Instruct:F16

Run and chat with the model

lemonade run user.SmolLM2-135M-Instruct-F16

List all available models

lemonade list

Atomic Chat

F32: PPL = 32.7182 +/- 1.71769

F16: PPL = 32.7181 +/- 1.71770

Q8_0: PPL = 32.8167 +/- 1.72386

Q8_0_imatrix: PPL = 32.8167 +/- 1.72386

Q6_k: PPL = 32.8940 +/- 1.72423

Q6_k_imatrix: PPL = 32.6484 +/- 1.70532

Q5_k: PPL = 34.2154 +/- 1.81195

Q5_k_imatrix: PPL = 32.9705 +/- 1.72225

Q4_k: PPL = 33.3240 +/- 1.70520

Q4_k_imatrix: PPL = 32.4122 +/- 1.65334

Q3_k: PPL = 36.7779 +/- 1.97784

Q3_k_imatrix: PPL = 33.3135 +/- 1.72823

Q2_k: PPL = 42.4066 +/- 2.21654

Q2_k_imatrix: PPL = 36.7429 +/- 1.85125

iQ1_s_imatrix: PPL = 68.2231 +/- 3.41196

Downloads last month: 46

GGUF

Model size

0.1B params

Architecture

llama

Hardware compatibility

1-bit

2-bit

6-bit

8-bit

16-bit

32-bit

Inference Providers NEW

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