OFFELLIA-FNORD-LFM2-24B-A2B-heretic-ara-MXFP4-MOE
OFFELLIA-FNORD-LFM2-24B-A2B-heretic-ara-MXFP4-MOE (Brunobkr, 2026) is a 24 billion parameter chat model. OFFELLIA-FNORD-LFM2-24B-A2B-heretic-ara-MXFP4-MOE is an open-weights chat model with roughly 24 billion parameters.
by Brunobkr · 24B parameters
Best for
- low-latency chat and routing
- request routing and triage
- text classification
Ways to use OFFELLIA-FNORD-LFM2-24B-A2B-heretic-ara-MXFP4-MOE in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your Brunobkr API key. osFoundry discovers OFFELLIA-FNORD-LFM2-24B-A2B-heretic-ara-MXFP4-MOE 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
OFFELLIA-FNORD-LFM2-24B-A2B-heretic-ara-MXFP4-MOE 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 OFFELLIA-FNORD-LFM2-24B-A2B-heretic-ara-MXFP4-MOE
OFFELLIA-FNORD-LFM2-24B-A2B-heretic-ara-MXFP4-MOE 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).
OFFELLIA-FNORD-LFM2-24B-A2B-heretic-ara-MXFP4-MOE vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about OFFELLIA-FNORD-LFM2-24B-A2B-heretic-ara-MXFP4-MOE
Is OFFELLIA-FNORD-LFM2-24B-A2B-heretic-ara-MXFP4-MOE free to use?
OFFELLIA-FNORD-LFM2-24B-A2B-heretic-ara-MXFP4-MOE 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 OFFELLIA-FNORD-LFM2-24B-A2B-heretic-ara-MXFP4-MOE 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 OFFELLIA-FNORD-LFM2-24B-A2B-heretic-ara-MXFP4-MOE need?
Approximately 15 GB at Q4 quantisation, or 58 GB at full FP16 precision. Fits on a single 24GB consumer GPU.
Can I run OFFELLIA-FNORD-LFM2-24B-A2B-heretic-ara-MXFP4-MOE locally?
Yes. OFFELLIA-FNORD-LFM2-24B-A2B-heretic-ara-MXFP4-MOE is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is OFFELLIA-FNORD-LFM2-24B-A2B-heretic-ara-MXFP4-MOE best at?
OFFELLIA-FNORD-LFM2-24B-A2B-heretic-ara-MXFP4-MOE is well-suited to low-latency chat and routing, request routing and triage, text classification.
How do I use OFFELLIA-FNORD-LFM2-24B-A2B-heretic-ara-MXFP4-MOE in osFoundry?
Paste your Brunobkr API key in the key dialog (or deploy the open weights for self-hostable models), assign OFFELLIA-FNORD-LFM2-24B-A2B-heretic-ara-MXFP4-MOE to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by Brunobkr on April 18, 2026. Source: https://huggingface.co/Brunobkr/OFFELLIA-FNORD-LFM2-24B-A2B-heretic-ara-MXFP4-MOE