Bielik-11B-v3.0-mlx-q4
LibraxisAI's Bielik-11B-v3.0-mlx-q4 packs 11 billion parameters into a chat model. Bielik-11B-v3.0-mlx-q4 is an open-weights chat model with roughly 11 billion parameters.
by LibraxisAI · 11B parameters
Best for
Ways to use Bielik-11B-v3.0-mlx-q4 in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your LibraxisAI API key. osFoundry discovers Bielik-11B-v3.0-mlx-q4 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
Bielik-11B-v3.0-mlx-q4 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 Bielik-11B-v3.0-mlx-q4
Bielik-11B-v3.0-mlx-q4 runs on a single 16GB consumer GPU (~7 GB VRAM with KV-cache headroom). Full-precision inference fits on a single H100 80GB at FP16 precision (~27 GB).
Bielik-11B-v3.0-mlx-q4 vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about Bielik-11B-v3.0-mlx-q4
Is Bielik-11B-v3.0-mlx-q4 free to use?
Bielik-11B-v3.0-mlx-q4 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 Bielik-11B-v3.0-mlx-q4 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 Bielik-11B-v3.0-mlx-q4 need?
Approximately 7 GB at Q4 quantisation, or 27 GB at full FP16 precision. Fits on a single 24GB consumer GPU.
Can I run Bielik-11B-v3.0-mlx-q4 locally?
Yes. Bielik-11B-v3.0-mlx-q4 is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is Bielik-11B-v3.0-mlx-q4 best at?
Bielik-11B-v3.0-mlx-q4 is well-suited to text generation.
How do I use Bielik-11B-v3.0-mlx-q4 in osFoundry?
Paste your LibraxisAI API key in the key dialog (or deploy the open weights for self-hostable models), assign Bielik-11B-v3.0-mlx-q4 to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by LibraxisAI on January 10, 2026. Source: https://huggingface.co/LibraxisAI/Bielik-11B-v3.0-mlx-q4