Monstral-123B-v2_GGUF
MarsupialAI's Monstral-123B-v2_GGUF packs 123 billion parameters into a chat model. Monstral-123B-v2_GGUF is an open-weights chat model with roughly 123 billion parameters.
by MarsupialAI · 123B parameters
Best for
Ways to use Monstral-123B-v2_GGUF in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your MarsupialAI API key. osFoundry discovers Monstral-123B-v2_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
Monstral-123B-v2_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 Monstral-123B-v2_GGUF
Monstral-123B-v2_GGUF runs on a single A100 80GB or H100 80GB at Q4 quantisation (~74 GB VRAM with KV-cache headroom). Full-precision inference requires multiple H100/H200 GPUs at FP16 (~296 GB).
Monstral-123B-v2_GGUF vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about Monstral-123B-v2_GGUF
Is Monstral-123B-v2_GGUF free to use?
Monstral-123B-v2_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 Monstral-123B-v2_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 Monstral-123B-v2_GGUF need?
Approximately 74 GB at Q4 quantisation, or 296 GB at full FP16 precision. Fits on a single A100/H100 80GB.
Can I run Monstral-123B-v2_GGUF locally?
Yes. Monstral-123B-v2_GGUF is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is Monstral-123B-v2_GGUF best at?
Monstral-123B-v2_GGUF is well-suited to text generation.
How do I use Monstral-123B-v2_GGUF in osFoundry?
Paste your MarsupialAI API key in the key dialog (or deploy the open weights for self-hostable models), assign Monstral-123B-v2_GGUF to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by MarsupialAI on December 3, 2024. Source: https://huggingface.co/MarsupialAI/Monstral-123B-v2_GGUF