2b1522e6-bef2-7cc4-831b-3794a31bcfdb
Released by phungkhaccuong in 2025, 2b1522e6-bef2-7cc4-831b-3794a31bcfdb is a 831 billion parameter chat model. 2b1522e6-bef2-7cc4-831b-3794a31bcfdb is an open-weights chat model with roughly 831 billion parameters.
by phungkhaccuong · 831B parameters
Best for
- complex multi-step reasoning
- agent orchestration with tool use
- long-document analysis and summarisation
Ways to use 2b1522e6-bef2-7cc4-831b-3794a31bcfdb in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your phungkhaccuong API key. osFoundry discovers 2b1522e6-bef2-7cc4-831b-3794a31bcfdb 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
2b1522e6-bef2-7cc4-831b-3794a31bcfdb 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 2b1522e6-bef2-7cc4-831b-3794a31bcfdb
2b1522e6-bef2-7cc4-831b-3794a31bcfdb runs on a multi-GPU setup or H200 141GB at Q4 (~499 GB VRAM with KV-cache headroom). Full-precision inference requires multiple H100/H200 GPUs at FP16 (~1995 GB).
2b1522e6-bef2-7cc4-831b-3794a31bcfdb vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about 2b1522e6-bef2-7cc4-831b-3794a31bcfdb
Is 2b1522e6-bef2-7cc4-831b-3794a31bcfdb free to use?
2b1522e6-bef2-7cc4-831b-3794a31bcfdb 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 2b1522e6-bef2-7cc4-831b-3794a31bcfdb 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 2b1522e6-bef2-7cc4-831b-3794a31bcfdb need?
Approximately 499 GB at Q4 quantisation, or 1995 GB at full FP16 precision. Requires multi-GPU at higher quantisation.
Can I run 2b1522e6-bef2-7cc4-831b-3794a31bcfdb locally?
Yes. 2b1522e6-bef2-7cc4-831b-3794a31bcfdb is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is 2b1522e6-bef2-7cc4-831b-3794a31bcfdb best at?
2b1522e6-bef2-7cc4-831b-3794a31bcfdb is well-suited to complex multi-step reasoning, agent orchestration with tool use, long-document analysis and summarisation.
How do I use 2b1522e6-bef2-7cc4-831b-3794a31bcfdb in osFoundry?
Paste your phungkhaccuong API key in the key dialog (or deploy the open weights for self-hostable models), assign 2b1522e6-bef2-7cc4-831b-3794a31bcfdb to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by phungkhaccuong on January 9, 2025. Source: https://huggingface.co/phungkhaccuong/2b1522e6-bef2-7cc4-831b-3794a31bcfdb