USASI
Model release

SmolLM3 3B

Release in the SmolLM family · version SmolLM3-3B

Maintained by Hugging Face (Smol Models Research, HuggingFaceTB)110

SmolLM3-3B is the instruct model of Hugging Face's SmolLM3 release (July 2025), a 3B-parameter decoder-only transformer pretrained on about 11 trillion tokens of web, code, math, and reasoning data in stages, then mid-trained on reasoning data and aligned with supervised fine-tuning and Anchored Preference Optimization. It can answer with or without an extended reasoning trace, supports tool calling, and natively covers six European languages.12

Last reviewedEntry updated Documented release Jul 8, 2025

Availability and license

Overall availability

Public

Downloadable from Hugging Face without gating.1

Availability is separate from permission: read the license before using or redistributing.

The post-training dataset SmolTalk2 states that its newly created subsets are Apache 2.0 and that the existing public datasets it includes keep their original licenses.9

Model-disclosure tier

Computed from the checklist below using USASI rubric v0.1. An editorial category, not a certification.
Model-disclosure tier (USASI rubric v0.1): Fully open

Every item in the model checklist is public, including the training data itself, and the weights and code are under OSI-approved licenses.

How tiers are computed

Public materials checklist

Items for a model under USASI rubric v0.1. Unknown means unassessed or insufficient evidence.
Public materials checklist for SmolLM3 3B
ItemStatusNotes and evidence
WeightsCan the general public download the model parameters for this release?PublicFinal weights are on Hugging Face without gating; intermediate checkpoints, including mid-training and SFT checkpoints, are published separately.1
Inference codeIs code for running the model published?PublicThe card documents inference with Transformers v4.53.0 or later and with vLLM and SGLang, and lists quantized options for llama.cpp, ONNX, MLX, MLC, and ExecuTorch.1
Training codeIs the code used to train the model published?PublicNanotron pretraining configs for the three stages and long-context extension are in the huggingface/smollm repository; the mid-training, SFT, and APO configs are in the alignment-handbook SmolLM3 recipe.146
Training-data informationPublic = the training data itself can be obtained. Partial = composition or sources are documented without full access.PublicThe pretraining datasets are listed in a public Hugging Face collection, and the mid-training, SFT, and preference data are published as SmolTalk2. Several listed datasets are published by third parties (for example DCLM and The Stack v2) under their own terms.189
Training recipeAre the training configuration and procedure documented in enough detail to follow?PublicThe blog post gives the web, code, and math proportions for each pretraining stage, the long-context extension, and the post-training stages; the configs include exact data weights.2
Evaluation materialsPublic = evaluation code or prompts that let others re-run the evaluations are published. Partial = results only.PublicThe card reports base and instruct evaluation results run with Hugging Face's lighteval and states that evaluation configs and code are in the huggingface/smollm repository.1

What it is useful for

The model card documents chat with switchable extended thinking (/think and /no_think), tool calling with XML- or Python-style tool definitions, and long inputs; the SmolLM repository describes the family as small enough for on-device use.13

Run and use notes

Documented facts only. No hardware or performance claims are made without a cited source and stated assumptions.
  • The card states the shipped config supports 65,536-token context and describes enabling YaRN rope scaling (factor 2.0) for inputs up to about 128k tokens; it recommends temperature 0.6 and top_p 0.95.1

Organization context

Provenance and derivatives

Post-trained by Hugging Face from its own SmolLM3-3B-Base, which was pretrained from scratch on public datasets. The mid-training data (NVIDIA's Llama-Nemotron post-training dataset and OpenThoughts3) contains reasoning traces, and several SmolTalk2 SFT subsets were generated with Qwen3-32B or DeepSeek-V3, so the post-training data includes outputs of third-party models.1289

Other releases in the SmolLM family

No other releases in this family have been assessed.

SmolLM family overview

U.S. eligibility

Project eligibility rests on documented governing or maintaining entities, not on contributors.

Eligible · basis: U.S. headquarters

Developed and published by Hugging Face's HuggingFaceTB organization ("Hugging Face Smol Models Research"). Hugging Face's terms of service identify Hugging Face, Inc., a Delaware corporation, as the provider of its services, and its privacy policy states that the company is located in the United States. See the hugging-face organization record for the dual-country assessment.1101112

Assessed Sep 29, 2026

Sources

  1. 1.
    HuggingFaceTB/SmolLM3-3B model card (external site: huggingface.co)

    Hugging Face · Model card · accessed Sep 29, 2026

  2. 2.
    SmolLM3: smol, multilingual, long-context reasoner (external site: huggingface.co)

    Hugging Face · Announcement · published Jul 8, 2025 · accessed Sep 29, 2026

  3. 3.
  4. 4.
    SmolLM family README (text/) (external site: raw.githubusercontent.com)

    Hugging Face · Documentation · accessed Sep 29, 2026

  5. 5.
    huggingface/smollm LICENSE (external site: raw.githubusercontent.com)

    Hugging Face · License · accessed Sep 29, 2026

  6. 6.
  7. 7.
  8. 8.
  9. 9.
    HuggingFaceTB/smoltalk2 dataset card (external site: huggingface.co)

    Hugging Face · Dataset card · accessed Sep 29, 2026

  10. 10.
    HuggingFaceTB (Hugging Face Smol Models Research) (external site: huggingface.co)

    Hugging Face · Official page · accessed Sep 29, 2026

  11. 11.
    Terms of Service (external site: huggingface.co)

    Hugging Face · Official page · accessed Sep 29, 2026

  12. 12.
    Hugging Face Privacy Policy (external site: huggingface.co)

    Hugging Face · Official page · accessed Sep 29, 2026

This listing is not an endorsement, a safety assessment, or a federal approval.

Support Us

Help keep USASI useful.

Optional. No USASI account required. Payment takes place on the linked provider’s website (Buy Me a Coffee).

About supporting this project