0d8b128b-8753-46c3-b80f-32427bd53cae
0d8b128b-8753-46c3-b80f-32427bd53cae is a 128 billion parameter chat model from nbninh, released January 14, 2025. 0d8b128b-8753-46c3-b80f-32427bd53cae is an open-weights chat model with roughly 128 billion parameters.
by nbninh · 128B parameters
Best for
- complex multi-step reasoning
- agent orchestration with tool use
- long-document analysis and summarisation
Ways to use 0d8b128b-8753-46c3-b80f-32427bd53cae in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your nbninh API key. osFoundry discovers 0d8b128b-8753-46c3-b80f-32427bd53cae 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
0d8b128b-8753-46c3-b80f-32427bd53cae 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 0d8b128b-8753-46c3-b80f-32427bd53cae
0d8b128b-8753-46c3-b80f-32427bd53cae runs on a single A100 80GB or H100 80GB at Q4 quantisation (~77 GB VRAM with KV-cache headroom). Full-precision inference requires multiple H100/H200 GPUs at FP16 (~308 GB).
0d8b128b-8753-46c3-b80f-32427bd53cae vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about 0d8b128b-8753-46c3-b80f-32427bd53cae
Is 0d8b128b-8753-46c3-b80f-32427bd53cae free to use?
0d8b128b-8753-46c3-b80f-32427bd53cae 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 0d8b128b-8753-46c3-b80f-32427bd53cae 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 0d8b128b-8753-46c3-b80f-32427bd53cae need?
Approximately 77 GB at Q4 quantisation, or 308 GB at full FP16 precision. Fits on a single A100/H100 80GB.
Can I run 0d8b128b-8753-46c3-b80f-32427bd53cae locally?
Yes. 0d8b128b-8753-46c3-b80f-32427bd53cae is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is 0d8b128b-8753-46c3-b80f-32427bd53cae best at?
0d8b128b-8753-46c3-b80f-32427bd53cae is well-suited to complex multi-step reasoning, agent orchestration with tool use, long-document analysis and summarisation.
How do I use 0d8b128b-8753-46c3-b80f-32427bd53cae in osFoundry?
Paste your nbninh API key in the key dialog (or deploy the open weights for self-hostable models), assign 0d8b128b-8753-46c3-b80f-32427bd53cae to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by nbninh on January 14, 2025. Source: https://huggingface.co/nbninh/0d8b128b-8753-46c3-b80f-32427bd53cae