kratark/SmolLM2-135M.gguf overview
SmolLM2 135M GGUF This repository contains a converted version of the SmolLM2 135M model in GGUF format , optimized for CPU and local inference. Original model…
Runs locally from ~258.3 MB disk (4 GB VRAM class GPUs with llama.cpp / guIDE).
Repository Files & Downloads
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| SmolLM2-135M.gguf | GGUF | GGUF | 258.3 MB | Download |
Model Details
| Model ID | kratark/SmolLM2-135M.gguf |
|---|---|
| Author | kratark |
| Pipeline | text-generation |
| License | apache-2.0 |
| Base model | HuggingFaceTB/SmolLM2-135M |
| Last modified | 2026-06-08T21:57:43.000Z |
Model README
---
language:
- en
license: apache-2.0
tags:
- gguf
- llama.cpp
- text-generation
base_model:
- HuggingFaceTB/SmolLM2-135M
library_name: transformers
pipeline_tag: text-generation
---
SmolLM2-135M-GGUF
This repository contains a converted version of the SmolLM2-135M model in GGUF format, optimized for CPU and local inference.
Original model:
https://huggingface.co/HuggingFaceTB/SmolLM2-135M
---
Model Description
SmolLM2-135M is a small language model created by Hugging Face for efficient text generation with low resource usage.
This repository does not modify or retrain the model.
It only includes:
- Conversion from Transformers → GGUF format
- Preparation for inference with tools like llama.cpp
---
Usage
llama.cpp example
./main -m smollm2-135m.gguf -p "Gravity is"Run kratark/SmolLM2-135M.gguf with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.
Source: Hugging Face · Compare models