causal_classifier_base_2025b
Released by againeureka in 2025, causal_classifier_base_2025b is a 2025 billion parameter chat model. causal_classifier_base_2025b is an open-weights chat model with roughly 2025 billion parameters.
by againeureka · 2025B parameters
Best for
- complex multi-step reasoning
- agent orchestration with tool use
- long-document analysis and summarisation
Ways to use causal_classifier_base_2025b in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your againeureka API key. osFoundry discovers causal_classifier_base_2025b 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
causal_classifier_base_2025b 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.
What hardware can run causal_classifier_base_2025b
causal_classifier_base_2025b runs on a multi-GPU setup or H200 141GB at Q4 (~1215 GB VRAM with KV-cache headroom). Full-precision inference requires multiple H100/H200 GPUs at FP16 (~4860 GB).
causal_classifier_base_2025b vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about causal_classifier_base_2025b
Is causal_classifier_base_2025b free to use?
causal_classifier_base_2025b 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 causal_classifier_base_2025b commercially?
Commercial use is allowed with conditions. Licence terms not specified — verify the upstream model card before commercial use. Check upstream documentation.
How much VRAM does causal_classifier_base_2025b need?
Approximately 1215 GB at Q4 quantisation, or 4860 GB at full FP16 precision. Requires multi-GPU at higher quantisation.
Can I run causal_classifier_base_2025b locally?
Yes. causal_classifier_base_2025b is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is causal_classifier_base_2025b best at?
causal_classifier_base_2025b is well-suited to complex multi-step reasoning, agent orchestration with tool use, long-document analysis and summarisation.
How do I use causal_classifier_base_2025b in osFoundry?
Paste your againeureka API key in the key dialog (or deploy the open weights for self-hostable models), assign causal_classifier_base_2025b to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by againeureka on August 20, 2025. Source: https://huggingface.co/againeureka/causal_classifier_base_2025b