🧠 SmolLM3‑3B‑Base GGUF Quantized

This is a quantized GGUF version of HuggingFaceTB/SmolLM3-3B-Base, optimized for fast, local inference using llama.cpp, llm-gguf, or Ollama.

For training details, tokenizer, chat format, and architecture: 👉 SmolLM3‑3B‑Base on Hugging Face

GGUF

Model size

3.08B params

Architecture

smollm3

Hardware compatibility

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

32-bit

Inference Providers NEW

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

Model tree for yasserrmd/smollm3-gguf

Base model

Finetuned

Quantized

(51)

this model