Step-3.5-Flash-REAP-121B-A11B-4bit
Released by NexVeridian in 2026, Step-3.5-Flash-REAP-121B-A11B-4bit is a 121 billion parameter chat model. Step-3.5-Flash-REAP-121B-A11B-4bit is an open-weights chat model with roughly 121 billion parameters.
by NexVeridian · 121B parameters
Best for
Ways to use Step-3.5-Flash-REAP-121B-A11B-4bit in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your NexVeridian API key. osFoundry discovers Step-3.5-Flash-REAP-121B-A11B-4bit 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
Step-3.5-Flash-REAP-121B-A11B-4bit 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 Step-3.5-Flash-REAP-121B-A11B-4bit
Step-3.5-Flash-REAP-121B-A11B-4bit runs on a single A100 80GB or H100 80GB at Q4 quantisation (~73 GB VRAM with KV-cache headroom). Full-precision inference requires multiple H100/H200 GPUs at FP16 (~291 GB).
Step-3.5-Flash-REAP-121B-A11B-4bit vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about Step-3.5-Flash-REAP-121B-A11B-4bit
Is Step-3.5-Flash-REAP-121B-A11B-4bit free to use?
Step-3.5-Flash-REAP-121B-A11B-4bit 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 Step-3.5-Flash-REAP-121B-A11B-4bit 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 Step-3.5-Flash-REAP-121B-A11B-4bit need?
Approximately 73 GB at Q4 quantisation, or 291 GB at full FP16 precision. Fits on a single A100/H100 80GB.
Can I run Step-3.5-Flash-REAP-121B-A11B-4bit locally?
Yes. Step-3.5-Flash-REAP-121B-A11B-4bit is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is Step-3.5-Flash-REAP-121B-A11B-4bit best at?
Step-3.5-Flash-REAP-121B-A11B-4bit is well-suited to text generation.
How do I use Step-3.5-Flash-REAP-121B-A11B-4bit in osFoundry?
Paste your NexVeridian API key in the key dialog (or deploy the open weights for self-hostable models), assign Step-3.5-Flash-REAP-121B-A11B-4bit to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by NexVeridian on March 10, 2026. Source: https://huggingface.co/NexVeridian/Step-3.5-Flash-REAP-121B-A11B-4bit