ja-ko-vn-12b-v2-gguf
ja-ko-vn-12b-v2-gguf (hell0ks, 2025) is a 12 billion parameter chat model. ja-ko-vn-12b-v2-gguf is an open-weights chat model with roughly 12 billion parameters.
by hell0ks · 12B parameters
Best for
Ways to use ja-ko-vn-12b-v2-gguf in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your hell0ks API key. osFoundry discovers ja-ko-vn-12b-v2-gguf 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
ja-ko-vn-12b-v2-gguf 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 ja-ko-vn-12b-v2-gguf
ja-ko-vn-12b-v2-gguf runs on a single 16GB consumer GPU (~8 GB VRAM with KV-cache headroom). Full-precision inference fits on a single H100 80GB at FP16 precision (~29 GB).
ja-ko-vn-12b-v2-gguf vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about ja-ko-vn-12b-v2-gguf
Is ja-ko-vn-12b-v2-gguf free to use?
ja-ko-vn-12b-v2-gguf 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 ja-ko-vn-12b-v2-gguf 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 ja-ko-vn-12b-v2-gguf need?
Approximately 8 GB at Q4 quantisation, or 29 GB at full FP16 precision. Fits on a single 24GB consumer GPU.
Can I run ja-ko-vn-12b-v2-gguf locally?
Yes. ja-ko-vn-12b-v2-gguf is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is ja-ko-vn-12b-v2-gguf best at?
ja-ko-vn-12b-v2-gguf is well-suited to translation.
How do I use ja-ko-vn-12b-v2-gguf in osFoundry?
Paste your hell0ks API key in the key dialog (or deploy the open weights for self-hostable models), assign ja-ko-vn-12b-v2-gguf to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by hell0ks on December 13, 2025. Source: https://huggingface.co/hell0ks/ja-ko-vn-12b-v2-gguf