blip2-opt-6.7b-coco
Released by Salesforce in 2023, blip2-opt-6.7b-coco is a 7 billion parameter image-generation model. blip2-opt-6.7b-coco is an open-weights image model with roughly 7 billion parameters.
by Salesforce · 7B parameters
Best for
Ways to use blip2-opt-6.7b-coco in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your Salesforce API key. osFoundry discovers blip2-opt-6.7b-coco 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
blip2-opt-6.7b-coco 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 blip2-opt-6.7b-coco
blip2-opt-6.7b-coco runs on a single 16GB consumer GPU (~5 GB VRAM with KV-cache headroom). Full-precision inference fits on a single H100 80GB at FP16 precision (~17 GB).
blip2-opt-6.7b-coco vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about blip2-opt-6.7b-coco
Is blip2-opt-6.7b-coco free to use?
blip2-opt-6.7b-coco 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 blip2-opt-6.7b-coco 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 blip2-opt-6.7b-coco need?
Approximately 5 GB at Q4 quantisation, or 17 GB at full FP16 precision. Fits on a single 24GB consumer GPU.
Can I run blip2-opt-6.7b-coco locally?
Yes. blip2-opt-6.7b-coco is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is blip2-opt-6.7b-coco best at?
blip2-opt-6.7b-coco is well-suited to image text to text.
How do I use blip2-opt-6.7b-coco in osFoundry?
Paste your Salesforce API key in the key dialog (or deploy the open weights for self-hostable models), assign blip2-opt-6.7b-coco to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by Salesforce on February 7, 2023. Source: https://huggingface.co/Salesforce/blip2-opt-6.7b-coco