Mistral-Small-24B-Instruct-2501
Built by unsloth, Mistral-Small-24B-Instruct-2501 is a 24 billion parameter chat model. Mistral-Small-24B-Instruct-2501 is an open-weights chat model with roughly 24 billion parameters.
by unsloth · 24B parameters
Best for
Ways to use Mistral-Small-24B-Instruct-2501 in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your unsloth API key. osFoundry discovers Mistral-Small-24B-Instruct-2501 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
Mistral-Small-24B-Instruct-2501 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 Mistral-Small-24B-Instruct-2501
Mistral-Small-24B-Instruct-2501 runs on a single 16GB consumer GPU (~15 GB VRAM with KV-cache headroom). Full-precision inference fits on a single H100 80GB at FP16 precision (~58 GB).
Mistral-Small-24B-Instruct-2501 vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about Mistral-Small-24B-Instruct-2501
Is Mistral-Small-24B-Instruct-2501 free to use?
Mistral-Small-24B-Instruct-2501 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 Mistral-Small-24B-Instruct-2501 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 Mistral-Small-24B-Instruct-2501 need?
Approximately 15 GB at Q4 quantisation, or 58 GB at full FP16 precision. Fits on a single 24GB consumer GPU.
Can I run Mistral-Small-24B-Instruct-2501 locally?
Yes. Mistral-Small-24B-Instruct-2501 is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is Mistral-Small-24B-Instruct-2501 best at?
Mistral-Small-24B-Instruct-2501 is well-suited to text generation.
How do I use Mistral-Small-24B-Instruct-2501 in osFoundry?
Paste your unsloth API key in the key dialog (or deploy the open weights for self-hostable models), assign Mistral-Small-24B-Instruct-2501 to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by unsloth on January 30, 2025. Source: https://huggingface.co/unsloth/Mistral-Small-24B-Instruct-2501