InklingThinking Machines Lab
|
SmolVLMHugging Face
|
|||||
Related Products
|
||||||
About
Inkling is an open-weights multimodal AI model from Thinking Machines designed as a customizable foundation model for developers, researchers, and enterprises. The model is a Mixture-of-Experts transformer with 975 billion total parameters, 41 billion active parameters, and support for context windows up to 1 million tokens. Inkling was trained from scratch on text, images, audio, and video, giving it native capabilities across reasoning, coding, agentic tool use, vision, audio, factuality, and instruction following. It is built with controllable thinking effort so users can balance performance, latency, and token efficiency for different workloads. The model is available for fine-tuning on Tinker, with playground access, API availability through ecosystem partners, and full weights published on Hugging Face. Built for customization, Inkling gives teams an open-weights base model for building domain-specific AI systems, multimodal agents, coding workflows, research tools, and more.
|
About
SmolVLM-Instruct is a compact, AI-powered multimodal model that combines the capabilities of vision and language processing, designed to handle tasks like image captioning, visual question answering, and multimodal storytelling. It works with both text and image inputs, providing highly efficient results while being optimized for smaller, resource-constrained environments. Built with SmolLM2 as its text decoder and SigLIP as its image encoder, the model offers improved performance for tasks that require integration of both textual and visual information. SmolVLM-Instruct can be fine-tuned for specific applications, offering businesses and developers a versatile tool for creating intelligent, interactive systems that require multimodal inputs.
|
|||||
Platforms Supported
Windows
Mac
Linux
Cloud
On-Premises
iPhone
iPad
Android
Chromebook
|
Platforms Supported
Windows
Mac
Linux
Cloud
On-Premises
iPhone
iPad
Android
Chromebook
|
|||||
Audience
AI developers, researchers, model fine-tuning teams, enterprise AI groups, agent builders, coding tool makers, multimodal AI teams, infrastructure providers, and organizations that need open-weights models for customization, long-context reasoning, vision, audio, tool use, and specialized AI applications
|
Audience
Developers, AI researchers, and businesses looking for a compact, high-performance model to handle multimodal tasks, including image-based data analysis, captioning, and story generation
|
|||||
Support
Phone Support
24/7 Live Support
Online
|
Support
Phone Support
24/7 Live Support
Online
|
|||||
API
Offers API
|
API
Offers API
|
|||||
Screenshots and Videos |
Screenshots and Videos |
|||||
Pricing
Free
Free Version
Free Trial
|
Pricing
Free
Open source
Free Version
Free Trial
|
|||||
Reviews/
|
Reviews/
|
|||||
Training
Documentation
Webinars
Live Online
In Person
|
Training
Documentation
Webinars
Live Online
In Person
|
|||||
Company InformationThinking Machines Lab
Founded: 2025
United States
thinkingmachines.ai/
|
Company InformationHugging Face
Founded: 2016
United States
huggingface.co/HuggingFaceTB/SmolVLM-Instruct
|
|||||
Alternatives |
Alternatives |
|||||
|
|
||||||
|
|
||||||
|
|
|
|||||
|
|
||||||
Categories |
Categories |
|||||
Integrations
Model Context Protocol (MCP)
Tinker
|
||||||
|
|
|