mistralai.Mistral-Large-3-675B-Instruct-2512-GGUF
DevQuasar's mistralai.Mistral-Large-3-675B-Instruct-2512-GGUF packs 675 billion parameters into a image-generation model. mistralai.Mistral-Large-3-675B-Instruct-2512-GGUF is an open-weights image model with roughly 675 billion parameters.
by DevQuasar · 675B parameters
Best for
Ways to use mistralai.Mistral-Large-3-675B-Instruct-2512-GGUF in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your DevQuasar API key. osFoundry discovers mistralai.Mistral-Large-3-675B-Instruct-2512-GGUF 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
mistralai.Mistral-Large-3-675B-Instruct-2512-GGUF 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 mistralai.Mistral-Large-3-675B-Instruct-2512-GGUF
mistralai.Mistral-Large-3-675B-Instruct-2512-GGUF runs on a multi-GPU setup or H200 141GB at Q4 (~405 GB VRAM with KV-cache headroom). Full-precision inference requires multiple H100/H200 GPUs at FP16 (~1620 GB).
mistralai.Mistral-Large-3-675B-Instruct-2512-GGUF vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about mistralai.Mistral-Large-3-675B-Instruct-2512-GGUF
Is mistralai.Mistral-Large-3-675B-Instruct-2512-GGUF free to use?
mistralai.Mistral-Large-3-675B-Instruct-2512-GGUF 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 mistralai.Mistral-Large-3-675B-Instruct-2512-GGUF 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 mistralai.Mistral-Large-3-675B-Instruct-2512-GGUF need?
Approximately 405 GB at Q4 quantisation, or 1620 GB at full FP16 precision. Requires multi-GPU at higher quantisation.
Can I run mistralai.Mistral-Large-3-675B-Instruct-2512-GGUF locally?
Yes. mistralai.Mistral-Large-3-675B-Instruct-2512-GGUF is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is mistralai.Mistral-Large-3-675B-Instruct-2512-GGUF best at?
mistralai.Mistral-Large-3-675B-Instruct-2512-GGUF is well-suited to image text to text.
How do I use mistralai.Mistral-Large-3-675B-Instruct-2512-GGUF in osFoundry?
Paste your DevQuasar API key in the key dialog (or deploy the open weights for self-hostable models), assign mistralai.Mistral-Large-3-675B-Instruct-2512-GGUF to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by DevQuasar on December 5, 2025. Source: https://huggingface.co/DevQuasar/mistralai.Mistral-Large-3-675B-Instruct-2512-GGUF