687b8c72-c89b-4cb7-b7c8-947509adff3c
Built by hongngo, 687b8c72-c89b-4cb7-b7c8-947509adff3c is a 89 billion parameter chat model. 687b8c72-c89b-4cb7-b7c8-947509adff3c is an open-weights chat model with roughly 89 billion parameters.
by hongngo · 89B parameters
Best for
- complex multi-step reasoning
- agent orchestration with tool use
- long-document analysis and summarisation
Ways to use 687b8c72-c89b-4cb7-b7c8-947509adff3c in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your hongngo API key. osFoundry discovers 687b8c72-c89b-4cb7-b7c8-947509adff3c 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
687b8c72-c89b-4cb7-b7c8-947509adff3c 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 687b8c72-c89b-4cb7-b7c8-947509adff3c
687b8c72-c89b-4cb7-b7c8-947509adff3c runs on a single A100 80GB or H100 80GB at Q4 quantisation (~54 GB VRAM with KV-cache headroom). Full-precision inference requires multiple H100/H200 GPUs at FP16 (~214 GB).
687b8c72-c89b-4cb7-b7c8-947509adff3c vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about 687b8c72-c89b-4cb7-b7c8-947509adff3c
Is 687b8c72-c89b-4cb7-b7c8-947509adff3c free to use?
687b8c72-c89b-4cb7-b7c8-947509adff3c 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 687b8c72-c89b-4cb7-b7c8-947509adff3c 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 687b8c72-c89b-4cb7-b7c8-947509adff3c need?
Approximately 54 GB at Q4 quantisation, or 214 GB at full FP16 precision. Fits on a single A100/H100 80GB.
Can I run 687b8c72-c89b-4cb7-b7c8-947509adff3c locally?
Yes. 687b8c72-c89b-4cb7-b7c8-947509adff3c is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is 687b8c72-c89b-4cb7-b7c8-947509adff3c best at?
687b8c72-c89b-4cb7-b7c8-947509adff3c is well-suited to complex multi-step reasoning, agent orchestration with tool use, long-document analysis and summarisation.
How do I use 687b8c72-c89b-4cb7-b7c8-947509adff3c in osFoundry?
Paste your hongngo API key in the key dialog (or deploy the open weights for self-hostable models), assign 687b8c72-c89b-4cb7-b7c8-947509adff3c to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by hongngo on January 13, 2025. Source: https://huggingface.co/hongngo/687b8c72-c89b-4cb7-b7c8-947509adff3c