splade-code-06B
splade-code-06B is a 6 billion parameter embedding model from naver, released February 24, 2026. splade-code-06B is an open-weights embed model with roughly 6 billion parameters.
by naver · 6B parameters
Best for
Ways to use splade-code-06B in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your naver API key. osFoundry discovers splade-code-06B 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
splade-code-06B 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 splade-code-06B
splade-code-06B runs on a single 16GB consumer GPU (~4 GB VRAM with KV-cache headroom). Full-precision inference fits on a single H100 80GB at FP16 precision (~15 GB).
splade-code-06B vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about splade-code-06B
Is splade-code-06B free to use?
splade-code-06B 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 splade-code-06B 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 splade-code-06B need?
Approximately 4 GB at Q4 quantisation, or 15 GB at full FP16 precision. Fits on a single 24GB consumer GPU.
Can I run splade-code-06B locally?
Yes. splade-code-06B is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is splade-code-06B best at?
splade-code-06B is well-suited to feature extraction.
How do I use splade-code-06B in osFoundry?
Paste your naver API key in the key dialog (or deploy the open weights for self-hostable models), assign splade-code-06B to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by naver on February 24, 2026. Source: https://huggingface.co/naver/splade-code-06B