Instructions to use prithivMLmods/SmolLM2-360M-F32-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use prithivMLmods/SmolLM2-360M-F32-GGUF with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="prithivMLmods/SmolLM2-360M-F32-GGUF")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("prithivMLmods/SmolLM2-360M-F32-GGUF", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use prithivMLmods/SmolLM2-360M-F32-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 prithivMLmods/SmolLM2-360M-F32-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf prithivMLmods/SmolLM2-360M-F32-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf prithivMLmods/SmolLM2-360M-F32-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf prithivMLmods/SmolLM2-360M-F32-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 prithivMLmods/SmolLM2-360M-F32-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf prithivMLmods/SmolLM2-360M-F32-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 prithivMLmods/SmolLM2-360M-F32-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf prithivMLmods/SmolLM2-360M-F32-GGUF:Q4_K_M

Use Docker

docker model run hf.co/prithivMLmods/SmolLM2-360M-F32-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use prithivMLmods/SmolLM2-360M-F32-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "prithivMLmods/SmolLM2-360M-F32-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "prithivMLmods/SmolLM2-360M-F32-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/prithivMLmods/SmolLM2-360M-F32-GGUF:Q4_K_M

SGLang

How to use prithivMLmods/SmolLM2-360M-F32-GGUF with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "prithivMLmods/SmolLM2-360M-F32-GGUF" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "prithivMLmods/SmolLM2-360M-F32-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "prithivMLmods/SmolLM2-360M-F32-GGUF" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "prithivMLmods/SmolLM2-360M-F32-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use prithivMLmods/SmolLM2-360M-F32-GGUF with Ollama:
```
ollama run hf.co/prithivMLmods/SmolLM2-360M-F32-GGUF:Q4_K_M
```
Unsloth Desktop
Docker Model Runner
How to use prithivMLmods/SmolLM2-360M-F32-GGUF with Docker Model Runner:
```
docker model run hf.co/prithivMLmods/SmolLM2-360M-F32-GGUF:Q4_K_M
```

Lemonade

How to use prithivMLmods/SmolLM2-360M-F32-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull prithivMLmods/SmolLM2-360M-F32-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.SmolLM2-360M-F32-GGUF-Q4_K_M

List all available models

lemonade list

Atomic Chat

prithivMLmods commited on Jun 7, 2025

Commit

7bcc1b2

verified ·

1 Parent(s): ff6145c

Update README.md

Browse files

Files changed (1) hide show

README.md +28 -1

README.md CHANGED Viewed

@@ -12,4 +12,31 @@ tags:
 # **SmolLM2-360M-Instruct**
-> [SmolLM2-360M-Instruct](HuggingFaceTB/SmolLM2-360M-Instruct) : The 360M model was trained on 4 trillion tokens using a diverse dataset combination: FineWeb-Edu, DCLM, The Stack, along with new filtered datasets we curated and will release soon. We developed the instruct version through supervised fine-tuning (SFT) using a combination of public datasets and our own curated datasets. We then applied Direct Preference Optimization (DPO) using UltraFeedback.

 # **SmolLM2-360M-Instruct**
+> [SmolLM2-360M-Instruct](HuggingFaceTB/SmolLM2-360M-Instruct) : The 360M model was trained on 4 trillion tokens using a diverse dataset combination: FineWeb-Edu, DCLM, The Stack, along with new filtered datasets we curated and will release soon. We developed the instruct version through supervised fine-tuning (SFT) using a combination of public datasets and our own curated datasets. We then applied Direct Preference Optimization (DPO) using UltraFeedback.
+## Model Files
+| File Name | Size | Format Description |
+|-----------|------|-------------------|
+| SmolLM2-360M-Instruct.F32.gguf | 1.45 GB | Full precision (32-bit floating point) |
+| SmolLM2-360M-Instruct.BF16.gguf | 726 MB | Brain floating point 16-bit |
+| SmolLM2-360M-Instruct.F16.gguf | 726 MB | Half precision (16-bit floating point) |
+| SmolLM2-360M-Instruct.Q8_0.gguf | 386 MB | 8-bit quantization |
+| SmolLM2-360M-Instruct.Q6_K.gguf | 367 MB | 6-bit quantization (K-quant) |
+| SmolLM2-360M-Instruct.Q5_K_M.gguf | 290 MB | 5-bit quantization (K-quant, medium) |
+| SmolLM2-360M-Instruct.Q5_K_S.gguf | 283 MB | 5-bit quantization (K-quant, small) |
+| SmolLM2-360M-Instruct.Q4_K_M.gguf | 271 MB | 4-bit quantization (K-quant, medium) |
+| SmolLM2-360M-Instruct.Q4_K_S.gguf | 260 MB | 4-bit quantization (K-quant, small) |
+| SmolLM2-360M-Instruct.Q3_K_L.gguf | 246 MB | 3-bit quantization (K-quant, large) |
+| SmolLM2-360M-Instruct.Q3_K_M.gguf | 235 MB | 3-bit quantization (K-quant, medium) |
+| SmolLM2-360M-Instruct.Q3_K_S.gguf | 219 MB | 3-bit quantization (K-quant, small) |
+| SmolLM2-360M-Instruct.Q2_K.gguf | 219 MB | 2-bit quantization (K-quant) |
+## Quants Usage
+(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
+Here is a handy graph by ikawrakow comparing some lower-quality quant
+types (lower is better):
+![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png)