Evidence checked Nov 11, 2026

Verified Nov 11, 2026 via SmolLM: smollm-hf-smollm3-3b-20261109bAI models

SmolLM

The README describes SmolLM, presented as Smol Models, as a Hugging Face family of compact open models for text and vision that are meant to run on-device.

Verified facts
8
Offers
1
Sources
2
Pricing
Free offer

Overview

What SmolLM covers

SmolLM, presented in the README as Smol Models, is a Hugging Face family of compact open models for text and vision that are meant to run on-device. The README highlights SmolLM3, a 3B model trained on 11T tokens, with an instruct variant that has think and no_think modes, support for six languages and long context up to 128k.

It also lists SmolVLM, a compact multimodal model for image and text tasks such as visual question answering and image description.

Read the full editorial overview

Licence and running it

The repository licence file is the Apache License, Version 2.0; the README itself does not state a licence. It says SmolLM3 is a fully open model with open weights and full training details, including the public data mixture and training configs.

The getting-started section loads SmolLM3 with Hugging Face Transformers on a GPU or CPU, and a tools folder holds local inference utilities. The README does not discuss pricing.

Maintenance and what is not established

The repository has no GitHub releases, so this capture follows the default branch. Its latest commit is dated 3 October 2026 and the repository is not archived.

The README is short, and its other linked documentation and model cards were not read; the SmolLM3-3B model card on Hugging Face was read and lists the Apache 2.0 licence. Performance comparisons in the README are the publisher's claims, and nothing was installed or tested.

Sources

SmolLM: smollm-project · Evidence: documentation · Not checked

Plans & prices

Prices as listed by SmolLM, before any tax or fee the pricing page does not state.

Scroll the table sideways for every column.

PlanRate period not stated
Plan: Self-hosted
FreeTax: Confirm at checkoutUpfront: not established
ConditionsModel card of HuggingFaceTB/SmolLM3-3B on Hugging Face, captured 9 November 2026; supplier description, not a deployment or test. The card lists the Apache-2.0 licence for SmolLM3-3B; the other models in the family were not checked one by one. Hardware, compute, accounts and any hosted service have separate costs and terms.
Unknown fees: Hardware and compute for running the modelVerified Nov 11, 2026

SmolLM: smollm-hf-smollm3-3b-20261109b

Documented facts

Each fact comes from official documentation and shows when it was verified.

  • Who it is for

    The README describes SmolLM, presented as Smol Models, as a Hugging Face family of compact open models for text and vision that are meant to run on-device.

    Verified Nov 8, 2026 · SmolLM: smollm-project

  • Coverage limits

    The README states that SmolLM3 supports six languages: English, French, Spanish, German, Italian and Portuguese.

    Verified Nov 8, 2026 · SmolLM: smollm-project

  • Provider

    Hugging Face

    Dated publisher project README captured on 9 November 2026 (commit 438be18d); names the publisher of the open models, not a hosted service.

    Verified Nov 11, 2026 · SmolLM: smollm-project

  • API model identifier

    HuggingFaceTB/SmolLM3-3B

    Model card of HuggingFaceTB/SmolLM3-3B on Hugging Face, captured 9 November 2026; supplier description, not a deployment or test. Hugging Face repository ID of the SmolLM3 3B instruct model; a named variant is evidence within the model family, not a separate product.

    Verified Nov 11, 2026 · SmolLM: smollm-hf-smollm3-3b-20261109b

  • Modalities

    Text language model

    Model card of HuggingFaceTB/SmolLM3-3B on Hugging Face, captured 9 November 2026; supplier description, not a deployment or test. Scope of the SmolLM3 language model only; the family's SmolVLM vision model is documented separately in the project README.

    Verified Nov 11, 2026 · SmolLM: smollm-hf-smollm3-3b-20261109b

  • Context window

    128K tokens (up to, with YaRN extrapolation)

    Model card of HuggingFaceTB/SmolLM3-3B on Hugging Face, captured 9 November 2026; supplier description, not a deployment or test. The card says the model was trained on 64k context and the shipped config.json is set for up to 65,536 tokens; reaching 128K needs the documented YaRN rope-scaling change. Quality at long lengths was not tested.

    Verified Nov 11, 2026 · SmolLM: smollm-hf-smollm3-3b-20261109b

  • Availability

    Local inference is documented with llama.cpp, ONNX, MLX, MLC and ExecuTorch, with quantized checkpoints in the publisher's collection.

    Model card of HuggingFaceTB/SmolLM3-3B on Hugging Face, captured 9 November 2026; supplier description, not a deployment or test. Documentation of local runtimes, not a performance claim or a hosted-service entitlement; the card also documents OpenAI-compatible serving with vLLM and SGLang.

    Verified Nov 11, 2026 · SmolLM: smollm-hf-smollm3-3b-20261109b

Applies to the facts above: Dated publisher project README captured on 7 November 2026; supplier description, not a deployment or independent test. Infrastructure, accounts, third-party services and managed offerings have separate costs and terms.

Not confirmed in our sources

We have not confirmed these terms for SmolLM in the linked documentation. That does not mean SmolLM lacks them; confirm them before you rely on them.

  • Maximum output
  • Input token rate
  • Output token rate

Sources & methodology

Facts come from the linked documentation. Documentation checks are not hands-on tests, and readable sources can have incomplete coverage.

Retrieved Nov 11, 2026
SmolLM: smollm-projectraw.githubusercontent.com
Retrieved Nov 11, 2026

Discovered an undocumented discrepancy or pricing shift? Submit a correction request.

Submit correction

SmolLM alternatives

Other AI models tools to weigh. Different billing units do not establish a cost winner, so compare plans side by side.

SmolLM comparisons

Compare two products in the same category using their documented terms and sources.