epe-3p-smollm-1p7b-100B-20n-2048sl-960gbsz-no_bce
epe-3p-smollm-1p7b-100B-20n-2048sl-960gbsz-no_bce is a 7 billion parameter chat model from Raghav-Singhal, released April 18, 2026. epe-3p-smollm-1p7b-100B-20n-2048sl-960gbsz-no_bce is an open-weights chat model with roughly 7 billion parameters.
by Raghav-Singhal · 7B parameters
Best for
Ways to use epe-3p-smollm-1p7b-100B-20n-2048sl-960gbsz-no_bce in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your Raghav-Singhal API key. osFoundry discovers epe-3p-smollm-1p7b-100B-20n-2048sl-960gbsz-no_bce 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
epe-3p-smollm-1p7b-100B-20n-2048sl-960gbsz-no_bce 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 epe-3p-smollm-1p7b-100B-20n-2048sl-960gbsz-no_bce
epe-3p-smollm-1p7b-100B-20n-2048sl-960gbsz-no_bce 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).
epe-3p-smollm-1p7b-100B-20n-2048sl-960gbsz-no_bce vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about epe-3p-smollm-1p7b-100B-20n-2048sl-960gbsz-no_bce
Is epe-3p-smollm-1p7b-100B-20n-2048sl-960gbsz-no_bce free to use?
epe-3p-smollm-1p7b-100B-20n-2048sl-960gbsz-no_bce 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 epe-3p-smollm-1p7b-100B-20n-2048sl-960gbsz-no_bce 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 epe-3p-smollm-1p7b-100B-20n-2048sl-960gbsz-no_bce need?
Approximately 5 GB at Q4 quantisation, or 17 GB at full FP16 precision. Fits on a single 24GB consumer GPU.
Can I run epe-3p-smollm-1p7b-100B-20n-2048sl-960gbsz-no_bce locally?
Yes. epe-3p-smollm-1p7b-100B-20n-2048sl-960gbsz-no_bce is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is epe-3p-smollm-1p7b-100B-20n-2048sl-960gbsz-no_bce best at?
epe-3p-smollm-1p7b-100B-20n-2048sl-960gbsz-no_bce is well-suited to text generation.
How do I use epe-3p-smollm-1p7b-100B-20n-2048sl-960gbsz-no_bce in osFoundry?
Paste your Raghav-Singhal API key in the key dialog (or deploy the open weights for self-hostable models), assign epe-3p-smollm-1p7b-100B-20n-2048sl-960gbsz-no_bce to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by Raghav-Singhal on April 18, 2026. Source: https://huggingface.co/Raghav-Singhal/epe-3p-smollm-1p7b-100B-20n-2048sl-960gbsz-no_bce