e2b-sft-fft-lug
Built by jq, e2b-sft-fft-lug is a 2 billion parameter image-generation model. e2b-sft-fft-lug is an open-weights image model with roughly 2 billion parameters.
by jq · 2B parameters
Best for
Ways to use e2b-sft-fft-lug in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your jq API key. osFoundry discovers e2b-sft-fft-lug 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
e2b-sft-fft-lug 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 e2b-sft-fft-lug
e2b-sft-fft-lug runs on a single 16GB consumer GPU (~2 GB VRAM with KV-cache headroom). Full-precision inference fits on a single H100 80GB at FP16 precision (~5 GB).
e2b-sft-fft-lug vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about e2b-sft-fft-lug
Is e2b-sft-fft-lug free to use?
e2b-sft-fft-lug 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 e2b-sft-fft-lug 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 e2b-sft-fft-lug need?
Approximately 2 GB at Q4 quantisation, or 5 GB at full FP16 precision. Fits on a single 24GB consumer GPU.
Can I run e2b-sft-fft-lug locally?
Yes. e2b-sft-fft-lug is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is e2b-sft-fft-lug best at?
e2b-sft-fft-lug is well-suited to image text to text.
How do I use e2b-sft-fft-lug in osFoundry?
Paste your jq API key in the key dialog (or deploy the open weights for self-hostable models), assign e2b-sft-fft-lug to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by jq on May 5, 2026. Source: https://huggingface.co/jq/e2b-sft-fft-lug