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

Libraries

How to use QuantLLM/SmolLM2-135M-QuantLLM with Transformers:

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

pipe = pipeline("text-generation", model="QuantLLM/SmolLM2-135M-QuantLLM")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("QuantLLM/SmolLM2-135M-QuantLLM")
model = AutoModelForCausalLM.from_pretrained("QuantLLM/SmolLM2-135M-QuantLLM")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use QuantLLM/SmolLM2-135M-QuantLLM with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "QuantLLM/SmolLM2-135M-QuantLLM"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "QuantLLM/SmolLM2-135M-QuantLLM",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/QuantLLM/SmolLM2-135M-QuantLLM

SGLang

How to use QuantLLM/SmolLM2-135M-QuantLLM 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 "QuantLLM/SmolLM2-135M-QuantLLM" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "QuantLLM/SmolLM2-135M-QuantLLM",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "QuantLLM/SmolLM2-135M-QuantLLM" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "QuantLLM/SmolLM2-135M-QuantLLM",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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

SmolLM2-135M-QuantLLM / README.md

codewithdark

Add model card

4711922 verified 12 days ago

preview code

raw

history blame contribute delete

3.69 kB

	---
	license: apache-2.0
	base_model: HuggingFaceTB/SmolLM2-135M
	library_name: transformers
	language:
	- en
	tags:
	- quantllm
	- transformers
	- safetensors
	pipeline_tag: text-generation
	---

	<div align="center">

	# 🤗 SmolLM2-135M-QuantLLM

	HuggingFaceTB/SmolLM2-135M converted to SAFETENSORS format

	[![QuantLLM](https://img.shields.io/badge/🚀_Made_with-QuantLLM-orange?style=for-the-badge)](https://github.com/codewithdark-git/QuantLLM)
	[![Format](https://img.shields.io/badge/Format-SAFETENSORS-blue?style=for-the-badge)]()


	<a href="https://github.com/codewithdark-git/QuantLLM">⭐ Star QuantLLM on GitHub</a>

	</div>

	---


	## 📖 About This Model

	This model is [HuggingFaceTB/SmolLM2-135M](https://huggingface.co/HuggingFaceTB/SmolLM2-135M) converted to SafeTensors format for use with HuggingFace Transformers and PyTorch.

	\| Property \| Value \|
	\|----------\|-------\|
	\| Base Model \| [HuggingFaceTB/SmolLM2-135M](https://huggingface.co/HuggingFaceTB/SmolLM2-135M) \|
	\| Format \| SAFETENSORS \|
	\| Quantization \| None (Full Precision) \|
	\| License \| apache-2.0 \|
	\| Created With \| [QuantLLM](https://github.com/codewithdark-git/QuantLLM) \|


	## 🚀 Quick Start

	### With Transformers

	```python
	from transformers import AutoModelForCausalLM, AutoTokenizer

	# Load model and tokenizer
	model = AutoModelForCausalLM.from_pretrained("codewithdark/SmolLM2-135M-QuantLLM")
	tokenizer = AutoTokenizer.from_pretrained("codewithdark/SmolLM2-135M-QuantLLM")

	# Generate text
	inputs = tokenizer("Once upon a time", return_tensors="pt")
	outputs = model.generate(**inputs, max_new_tokens=100, do_sample=True)
	print(tokenizer.decode(outputs[0], skip_special_tokens=True))
	```

	### With QuantLLM

	```python
	from quantllm import TurboModel

	# Load with automatic optimization
	model = TurboModel.from_pretrained("codewithdark/SmolLM2-135M-QuantLLM")

	# Generate
	response = model.generate("Write a poem about coding")
	print(response)
	```

	### Requirements

	```bash
	pip install transformers torch
	```


	## 📊 Model Details

	\| Property \| Value \|
	\|----------\|-------\|
	\| Original Model \| [HuggingFaceTB/SmolLM2-135M](https://huggingface.co/HuggingFaceTB/SmolLM2-135M) \|
	\| Format \| SAFETENSORS \|
	\| Quantization \| Full Precision \|
	\| License \| `apache-2.0` \|
	\| Export Date \| 2026-04-29 \|
	\| Exported By \| [QuantLLM v2.1](https://github.com/codewithdark-git/QuantLLM) \|



	---

	## 🚀 Created with QuantLLM

	<div align="center">

	[![QuantLLM](https://img.shields.io/badge/🚀_QuantLLM-Ultra--fast_LLM_Quantization-orange?style=for-the-badge)](https://github.com/codewithdark-git/QuantLLM)

	Convert any model to GGUF, ONNX, or MLX in one line!

	```python
	from quantllm import turbo

	# Load any HuggingFace model
	model = turbo("HuggingFaceTB/SmolLM2-135M")

	# Export to any format
	model.export("safetensors", quantization="Q4_K_M")

	# Push to HuggingFace
	model.push("your-repo", format="safetensors")
	```

	<a href="https://github.com/codewithdark-git/QuantLLM">
	<img src="https://img.shields.io/github/stars/codewithdark-git/QuantLLM?style=social" alt="GitHub Stars">
	</a>

	[📚 Documentation](https://github.com/codewithdark-git/QuantLLM#readme) ·
	[🐛 Report Issue](https://github.com/codewithdark-git/QuantLLM/issues) ·
	[💡 Request Feature](https://github.com/codewithdark-git/QuantLLM/issues)

	</div>


	## 📊 Export Details

	Exported with [QuantLLM](https://github.com/codewithdark-git/QuantLLM) from `HuggingFaceTB/SmolLM2-135M` (134.5M params).

	\| Property \| Value \|
	\|----------\|-------\|
	\| Format \| SafeTensors \|
	\| Size \| 541.6 MB \|
	\| Parameters \| 134.5M \|
	\| Dtype \| float32 \|

	### How to use