MiniCPM4.1-8B-AutoAWQ
openbmb's MiniCPM4.1-8B-AutoAWQ packs 8 billion parameters into a chat model. MiniCPM4.1-8B-AutoAWQ is an open-weights chat model with roughly 8 billion parameters.
by openbmb · 8B parameters
Best for
Ways to use MiniCPM4.1-8B-AutoAWQ in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your openbmb API key. osFoundry discovers MiniCPM4.1-8B-AutoAWQ 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
MiniCPM4.1-8B-AutoAWQ 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 MiniCPM4.1-8B-AutoAWQ
MiniCPM4.1-8B-AutoAWQ 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 (~20 GB).
MiniCPM4.1-8B-AutoAWQ vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about MiniCPM4.1-8B-AutoAWQ
Is MiniCPM4.1-8B-AutoAWQ free to use?
MiniCPM4.1-8B-AutoAWQ 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 MiniCPM4.1-8B-AutoAWQ 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 MiniCPM4.1-8B-AutoAWQ need?
Approximately 5 GB at Q4 quantisation, or 20 GB at full FP16 precision. Fits on a single 24GB consumer GPU.
Can I run MiniCPM4.1-8B-AutoAWQ locally?
Yes. MiniCPM4.1-8B-AutoAWQ is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is MiniCPM4.1-8B-AutoAWQ best at?
MiniCPM4.1-8B-AutoAWQ is well-suited to text generation.
How do I use MiniCPM4.1-8B-AutoAWQ in osFoundry?
Paste your openbmb API key in the key dialog (or deploy the open weights for self-hostable models), assign MiniCPM4.1-8B-AutoAWQ to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by openbmb on September 4, 2025. Source: https://huggingface.co/openbmb/MiniCPM4.1-8B-AutoAWQ