Mistral-Small-24B-Instruct-2501_GPTQ_G128_W4A16_MSE
ConfidentialMind's Mistral-Small-24B-Instruct-2501_GPTQ_G128_W4A16_MSE packs 24 billion parameters into a chat model. Mistral-Small-24B-Instruct-2501_GPTQ_G128_W4A16_MSE is an open-weights chat model with roughly 24 billion parameters.
by ConfidentialMind · 24B parameters
Best for
Ways to use Mistral-Small-24B-Instruct-2501_GPTQ_G128_W4A16_MSE in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your ConfidentialMind API key. osFoundry discovers Mistral-Small-24B-Instruct-2501_GPTQ_G128_W4A16_MSE 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_GPTQ_G128_W4A16_MSE 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_GPTQ_G128_W4A16_MSE
Mistral-Small-24B-Instruct-2501_GPTQ_G128_W4A16_MSE 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_GPTQ_G128_W4A16_MSE 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_GPTQ_G128_W4A16_MSE
Is Mistral-Small-24B-Instruct-2501_GPTQ_G128_W4A16_MSE free to use?
Mistral-Small-24B-Instruct-2501_GPTQ_G128_W4A16_MSE 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_GPTQ_G128_W4A16_MSE 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_GPTQ_G128_W4A16_MSE 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_GPTQ_G128_W4A16_MSE locally?
Yes. Mistral-Small-24B-Instruct-2501_GPTQ_G128_W4A16_MSE 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_GPTQ_G128_W4A16_MSE best at?
Mistral-Small-24B-Instruct-2501_GPTQ_G128_W4A16_MSE is well-suited to text classification.
How do I use Mistral-Small-24B-Instruct-2501_GPTQ_G128_W4A16_MSE in osFoundry?
Paste your ConfidentialMind API key in the key dialog (or deploy the open weights for self-hostable models), assign Mistral-Small-24B-Instruct-2501_GPTQ_G128_W4A16_MSE to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by ConfidentialMind on February 15, 2025. Source: https://huggingface.co/ConfidentialMind/Mistral-Small-24B-Instruct-2501_GPTQ_G128_W4A16_MSE