Codestral-22B-v0.1-4bit
mlx-community's Codestral-22B-v0.1-4bit packs 22 billion parameters into a chat model. Codestral-22B-v0.1-4bit is an open-weights chat model with roughly 22 billion parameters.
by mlx-community · 22B parameters
Best for
- low-latency chat and routing
- request routing and triage
- text classification
Ways to use Codestral-22B-v0.1-4bit in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your mlx-community API key. osFoundry discovers Codestral-22B-v0.1-4bit 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
Codestral-22B-v0.1-4bit 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 Codestral-22B-v0.1-4bit
Codestral-22B-v0.1-4bit runs on a single 16GB consumer GPU (~14 GB VRAM with KV-cache headroom). Full-precision inference fits on a single H100 80GB at FP16 precision (~53 GB).
Codestral-22B-v0.1-4bit vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about Codestral-22B-v0.1-4bit
Is Codestral-22B-v0.1-4bit free to use?
Codestral-22B-v0.1-4bit 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 Codestral-22B-v0.1-4bit 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 Codestral-22B-v0.1-4bit need?
Approximately 14 GB at Q4 quantisation, or 53 GB at full FP16 precision. Fits on a single 24GB consumer GPU.
Can I run Codestral-22B-v0.1-4bit locally?
Yes. Codestral-22B-v0.1-4bit is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is Codestral-22B-v0.1-4bit best at?
Codestral-22B-v0.1-4bit is well-suited to low-latency chat and routing, request routing and triage, text classification.
How do I use Codestral-22B-v0.1-4bit in osFoundry?
Paste your mlx-community API key in the key dialog (or deploy the open weights for self-hostable models), assign Codestral-22B-v0.1-4bit to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by mlx-community on May 29, 2024. Source: https://huggingface.co/mlx-community/Codestral-22B-v0.1-4bit