DeepSeek-Prover-V2-671B
Released by deepseek-ai in 2025, DeepSeek-Prover-V2-671B is a 671 billion parameter chat model. DeepSeek-Prover-V2-671B is an open-weights chat model with roughly 671 billion parameters.
by deepseek-ai · 671B parameters
Best for
Ways to use DeepSeek-Prover-V2-671B in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your deepseek-ai API key. osFoundry discovers DeepSeek-Prover-V2-671B 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
DeepSeek-Prover-V2-671B 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 DeepSeek-Prover-V2-671B
DeepSeek-Prover-V2-671B runs on a multi-GPU setup or H200 141GB at Q4 (~403 GB VRAM with KV-cache headroom). Full-precision inference requires multiple H100/H200 GPUs at FP16 (~1611 GB).
DeepSeek-Prover-V2-671B vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about DeepSeek-Prover-V2-671B
Is DeepSeek-Prover-V2-671B free to use?
DeepSeek-Prover-V2-671B 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 DeepSeek-Prover-V2-671B 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 DeepSeek-Prover-V2-671B need?
Approximately 403 GB at Q4 quantisation, or 1611 GB at full FP16 precision. Requires multi-GPU at higher quantisation.
Can I run DeepSeek-Prover-V2-671B locally?
Yes. DeepSeek-Prover-V2-671B is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is DeepSeek-Prover-V2-671B best at?
DeepSeek-Prover-V2-671B is well-suited to text generation.
How do I use DeepSeek-Prover-V2-671B in osFoundry?
Paste your deepseek-ai API key in the key dialog (or deploy the open weights for self-hostable models), assign DeepSeek-Prover-V2-671B to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by deepseek-ai on April 30, 2025. Source: https://huggingface.co/deepseek-ai/DeepSeek-Prover-V2-671B