Evidencia comprobada el 11 nov 2026

Comprobado el 11 nov 2026 vía SmolLM: smollm-hf-smollm3-3b-20261109bModelos de IA

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.

Datos verificados
8
Ofertas
1
Fuentes
2
Precios
Oferta gratuita

Planes y precios

Precios según SmolLM, sin impuestos ni cargos que su página de precios no indique.

Desplaza la tabla hacia los lados para ver todas las columnas.

PlanPeriodo de la tarifa no indicado
Plan: Self-hosted
GratisImpuestos: Confírmalos al pagarPago inicial: no confirmado
CondicionesModel 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.
Cargos desconocidos: Hardware and compute for running the modelComprobado el 11 nov 2026

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

Datos documentados

Cada dato procede de documentación oficial e indica cuándo se verificó.

  • Para quién

    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.

    Comprobado el 8 nov 2026 · SmolLM: smollm-project

  • Límites de cobertura

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

    Comprobado el 8 nov 2026 · SmolLM: smollm-project

  • Proveedor

    Hugging Face

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

    Comprobado el 11 nov 2026 · SmolLM: smollm-project

  • Identificador del modelo en la API

    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.

    Comprobado el 11 nov 2026 · SmolLM: smollm-hf-smollm3-3b-20261109b

  • Modalidades

    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.

    Comprobado el 11 nov 2026 · SmolLM: smollm-hf-smollm3-3b-20261109b

  • Ventana de contexto

    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.

    Comprobado el 11 nov 2026 · SmolLM: smollm-hf-smollm3-3b-20261109b

  • Disponibilidad

    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.

    Comprobado el 11 nov 2026 · SmolLM: smollm-hf-smollm3-3b-20261109b

Se aplica a los datos anteriores: 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.

Sin confirmar en nuestras fuentes

No hemos confirmado estas condiciones de SmolLM en la documentación enlazada. Eso no significa que SmolLM no las tenga; confírmalas antes de contar con ellas.

  • Salida máxima
  • Precio por token de entrada
  • Precio por token de salida

Fuentes y metodología

Los datos proceden de la documentación enlazada. Revisar documentación no equivale a probar el producto, y las fuentes legibles pueden tener una cobertura incompleta.

Obtenido: 11 nov 2026
SmolLM: smollm-projectraw.githubusercontent.com
Obtenido: 11 nov 2026

¿Has detectado una discrepancia no documentada o un cambio de precio? Envíanos una corrección.

No se ha publicado un contacto para correcciones.

Alternativas a SmolLM

Otras herramientas de modelos de IA que valorar. Las unidades de facturación distintas no permiten comparar costes directamente, así que compara los planes lado a lado.

Comparaciones de SmolLM

Compara dos productos de la misma categoría con sus condiciones documentadas y sus fuentes.