GLM-5-REAP-381B
Built by 0xSero, GLM-5-REAP-381B is a 381 billion parameter chat model. GLM-5-REAP-381B is an open-weights chat model with roughly 381 billion parameters.
by 0xSero · 381B parameters
Best for
Ways to use GLM-5-REAP-381B in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your 0xSero API key. osFoundry discovers GLM-5-REAP-381B 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
GLM-5-REAP-381B 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 GLM-5-REAP-381B
GLM-5-REAP-381B runs on a multi-GPU setup or H200 141GB at Q4 (~229 GB VRAM with KV-cache headroom). Full-precision inference requires multiple H100/H200 GPUs at FP16 (~915 GB).
GLM-5-REAP-381B vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about GLM-5-REAP-381B
Is GLM-5-REAP-381B free to use?
GLM-5-REAP-381B 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 GLM-5-REAP-381B 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 GLM-5-REAP-381B need?
Approximately 229 GB at Q4 quantisation, or 915 GB at full FP16 precision. Requires multi-GPU at higher quantisation.
Can I run GLM-5-REAP-381B locally?
Yes. GLM-5-REAP-381B is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is GLM-5-REAP-381B best at?
GLM-5-REAP-381B is well-suited to text generation.
How do I use GLM-5-REAP-381B in osFoundry?
Paste your 0xSero API key in the key dialog (or deploy the open weights for self-hostable models), assign GLM-5-REAP-381B to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by 0xSero on March 26, 2026. Source: https://huggingface.co/0xSero/GLM-5-REAP-381B