kanana-2-30b-a3b-instruct-2601
kakaocorp's kanana-2-30b-a3b-instruct-2601 packs 30 billion parameters into a chat model. kanana-2-30b-a3b-instruct-2601 is an open-weights chat model with roughly 30 billion parameters.
by kakaocorp · 30B parameters
Best for
Ways to use kanana-2-30b-a3b-instruct-2601 in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your kakaocorp API key. osFoundry discovers kanana-2-30b-a3b-instruct-2601 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
kanana-2-30b-a3b-instruct-2601 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 kanana-2-30b-a3b-instruct-2601
kanana-2-30b-a3b-instruct-2601 runs on a 24GB consumer or workstation GPU (~18 GB VRAM with KV-cache headroom). Full-precision inference fits on a single H100 80GB at FP16 precision (~72 GB).
kanana-2-30b-a3b-instruct-2601 vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about kanana-2-30b-a3b-instruct-2601
Is kanana-2-30b-a3b-instruct-2601 free to use?
kanana-2-30b-a3b-instruct-2601 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 kanana-2-30b-a3b-instruct-2601 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 kanana-2-30b-a3b-instruct-2601 need?
Approximately 18 GB at Q4 quantisation, or 72 GB at full FP16 precision. Fits on a single 24GB consumer GPU.
Can I run kanana-2-30b-a3b-instruct-2601 locally?
Yes. kanana-2-30b-a3b-instruct-2601 is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is kanana-2-30b-a3b-instruct-2601 best at?
kanana-2-30b-a3b-instruct-2601 is well-suited to text generation.
How do I use kanana-2-30b-a3b-instruct-2601 in osFoundry?
Paste your kakaocorp API key in the key dialog (or deploy the open weights for self-hostable models), assign kanana-2-30b-a3b-instruct-2601 to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by kakaocorp on January 14, 2026. Source: https://huggingface.co/kakaocorp/kanana-2-30b-a3b-instruct-2601