TerraMind-1.0-Tokenizer-S2L2A
Released by ibm-esa-geospatial in 2025, TerraMind-1.0-Tokenizer-S2L2A is an chat model. TerraMind-1.0-Tokenizer-S2L2A is an open-weights chat model.
by ibm-esa-geospatial
Best for
- low-latency chat and routing
- request routing and triage
- text classification
Ways to use TerraMind-1.0-Tokenizer-S2L2A in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your ibm-esa-geospatial API key. osFoundry discovers TerraMind-1.0-Tokenizer-S2L2A automatically — assign it to a Maestro role (router, direct, orchestrator, or fallback) in the Pipeline tab and it is live in every chat. Your key, your provider account — no token markup.
Deploy a dedicated endpoint
TerraMind-1.0-Tokenizer-S2L2A is open-weights — run it locally for free, or deploy a dedicated GPU endpoint in your workspace for reserved capacity with no rate limits.
Use it in a Room App
Room Apps declare AI features in their manifest, then call them with invokeAI:
import { invokeAI } from '@osfoundry/app-sdk'
// 'summarize' is an AI feature declared in your app manifest.
const result = await invokeAI('summarize', userText)
Call it from your own apps
Once a model is wired into your workspace you can host it as an API and reach it from your own services, scripts, or CI — outside osFoundry.
TerraMind-1.0-Tokenizer-S2L2A vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about TerraMind-1.0-Tokenizer-S2L2A
Is TerraMind-1.0-Tokenizer-S2L2A free to use?
TerraMind-1.0-Tokenizer-S2L2A is free to run locally on your own hardware. Hosted access through osFoundry is metered (input Free (local), output Free (local)). You can switch between local and hosted at any time.
Can I use TerraMind-1.0-Tokenizer-S2L2A commercially?
Commercial use is allowed with conditions. Licence terms not specified — verify the upstream model card before commercial use. Check upstream documentation.
Can I run TerraMind-1.0-Tokenizer-S2L2A locally?
Yes. TerraMind-1.0-Tokenizer-S2L2A is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is TerraMind-1.0-Tokenizer-S2L2A best at?
TerraMind-1.0-Tokenizer-S2L2A is well-suited to low-latency chat and routing, request routing and triage, text classification.
How do I use TerraMind-1.0-Tokenizer-S2L2A in osFoundry?
Paste your ibm-esa-geospatial API key in the key dialog (or deploy the open weights for self-hostable models), assign TerraMind-1.0-Tokenizer-S2L2A to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by ibm-esa-geospatial on February 20, 2025. Source: https://huggingface.co/ibm-esa-geospatial/TerraMind-1.0-Tokenizer-S2L2A