Loubna Ben Allal
Research Engineer at Hugging Face leading the SmolLM series of small open language models
- Research Engineer, Hugging Face12
Loubna Ben Allal is a Research Engineer at Hugging Face, working on training open foundation models from data curation through pretraining recipes and evaluation. Ben Allal's site says Ben Allal leads SmolLM, SmolLM2, and SmolLM3, Hugging Face's small open models built to run on-device, and Ben Allal is first author of the SmolLM2 paper, which released the model together with its new training datasets. The SmolLM3 model card points to llama.cpp, ONNX, MLX, MLC, and ExecuTorch for local inference.1354
Work
SmolLM
Leads the SmolLM, SmolLM2, and SmolLM3 releases, according to Ben Allal's site, and is first author of the SmolLM2 paper on data-centric training of a small language model. The project repository describes compact open models meant to run on-device and includes local inference guides.135
SmolLM3-3B
Part of the SmolLM3 work Ben Allal leads; the Apache-2.0 model card describes a 3B-parameter open model with quantized checkpoints for local runtimes.14
This profile covers public professional work only, from the sources below. It is not an endorsement or a ranking. To correct or remove it, use the correction form.