Instructions to use maxylium/SmolLM2-360M-Instruct-Distill-Reasoning-Mix-2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use maxylium/SmolLM2-360M-Instruct-Distill-Reasoning-Mix-2 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 maxylium/SmolLM2-360M-Instruct-Distill-Reasoning-Mix-2:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf maxylium/SmolLM2-360M-Instruct-Distill-Reasoning-Mix-2:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf maxylium/SmolLM2-360M-Instruct-Distill-Reasoning-Mix-2:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf maxylium/SmolLM2-360M-Instruct-Distill-Reasoning-Mix-2: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 maxylium/SmolLM2-360M-Instruct-Distill-Reasoning-Mix-2:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf maxylium/SmolLM2-360M-Instruct-Distill-Reasoning-Mix-2: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 maxylium/SmolLM2-360M-Instruct-Distill-Reasoning-Mix-2:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf maxylium/SmolLM2-360M-Instruct-Distill-Reasoning-Mix-2:Q4_K_M

Use Docker

docker model run hf.co/maxylium/SmolLM2-360M-Instruct-Distill-Reasoning-Mix-2:Q4_K_M

LM Studio
Jan
Ollama
How to use maxylium/SmolLM2-360M-Instruct-Distill-Reasoning-Mix-2 with Ollama:
```
ollama run hf.co/maxylium/SmolLM2-360M-Instruct-Distill-Reasoning-Mix-2:Q4_K_M
```
Unsloth Desktop
Docker Model Runner
How to use maxylium/SmolLM2-360M-Instruct-Distill-Reasoning-Mix-2 with Docker Model Runner:
```
docker model run hf.co/maxylium/SmolLM2-360M-Instruct-Distill-Reasoning-Mix-2:Q4_K_M
```

Lemonade

How to use maxylium/SmolLM2-360M-Instruct-Distill-Reasoning-Mix-2 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull maxylium/SmolLM2-360M-Instruct-Distill-Reasoning-Mix-2:Q4_K_M

Run and chat with the model

lemonade run user.SmolLM2-360M-Instruct-Distill-Reasoning-Mix-2-Q4_K_M

List all available models

lemonade list

Atomic Chat

SmolLM2-360M-Instruct-Distill-Reasoning-Mix-2 : GGUF

This model was finetuned and converted to GGUF format using Unsloth.

Example usage:

For text only LLMs: llama-cli -hf maxylium/SmolLM2-360M-Instruct-Distill-Reasoning-Mix-2 --jinja
For multimodal models: llama-mtmd-cli -hf maxylium/SmolLM2-360M-Instruct-Distill-Reasoning-Mix-2 --jinja

Available Model files:

checkpoint-139.Q8_0.gguf
checkpoint-139.F16.gguf
checkpoint-139.BF16.gguf
checkpoint-139.Q2_K_L.gguf
checkpoint-139.Q3_K_M.gguf
checkpoint-139.Q5_K_M.gguf
checkpoint-139.Q4_K_M.gguf This was trained 2x faster with Unsloth

Downloads last month: 77

GGUF

Model size

0.4B params

Architecture

llama

Hardware compatibility

2-bit

3-bit

4-bit

5-bit

8-bit

16-bit

Inference Providers NEW

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