Devstral-Small-2-24B-Instruct-2512-MLX-3bit
badmadrad's Devstral-Small-2-24B-Instruct-2512-MLX-3bit packs 24 billion parameters into a chat model. Devstral-Small-2-24B-Instruct-2512-MLX-3bit is an open-weights chat model with roughly 24 billion parameters.
by badmadrad · 24B parameters
Best for
Ways to use Devstral-Small-2-24B-Instruct-2512-MLX-3bit in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your badmadrad API key. osFoundry discovers Devstral-Small-2-24B-Instruct-2512-MLX-3bit 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
Devstral-Small-2-24B-Instruct-2512-MLX-3bit 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 Devstral-Small-2-24B-Instruct-2512-MLX-3bit
Devstral-Small-2-24B-Instruct-2512-MLX-3bit 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).
Devstral-Small-2-24B-Instruct-2512-MLX-3bit vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about Devstral-Small-2-24B-Instruct-2512-MLX-3bit
Is Devstral-Small-2-24B-Instruct-2512-MLX-3bit free to use?
Devstral-Small-2-24B-Instruct-2512-MLX-3bit 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 Devstral-Small-2-24B-Instruct-2512-MLX-3bit 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 Devstral-Small-2-24B-Instruct-2512-MLX-3bit need?
Approximately 15 GB at Q4 quantisation, or 58 GB at full FP16 precision. Fits on a single 24GB consumer GPU.
Can I run Devstral-Small-2-24B-Instruct-2512-MLX-3bit locally?
Yes. Devstral-Small-2-24B-Instruct-2512-MLX-3bit is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is Devstral-Small-2-24B-Instruct-2512-MLX-3bit best at?
Devstral-Small-2-24B-Instruct-2512-MLX-3bit is well-suited to text generation.
How do I use Devstral-Small-2-24B-Instruct-2512-MLX-3bit in osFoundry?
Paste your badmadrad API key in the key dialog (or deploy the open weights for self-hostable models), assign Devstral-Small-2-24B-Instruct-2512-MLX-3bit to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by badmadrad on February 13, 2026. Source: https://huggingface.co/badmadrad/Devstral-Small-2-24B-Instruct-2512-MLX-3bit