Apriel-15B-type6-e5-max-1e4-alpha0_25
Apriel-15B-type6-e5-max-1e4-alpha0_25 (yufeng1, 2026) is a 15 billion parameter chat model. Apriel-15B-type6-e5-max-1e4-alpha0_25 is an open-weights chat model with roughly 15 billion parameters.
by yufeng1 · 15B parameters
Best for
Ways to use Apriel-15B-type6-e5-max-1e4-alpha0_25 in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your yufeng1 API key. osFoundry discovers Apriel-15B-type6-e5-max-1e4-alpha0_25 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
Apriel-15B-type6-e5-max-1e4-alpha0_25 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 Apriel-15B-type6-e5-max-1e4-alpha0_25
Apriel-15B-type6-e5-max-1e4-alpha0_25 runs on a single 16GB consumer GPU (~9 GB VRAM with KV-cache headroom). Full-precision inference fits on a single H100 80GB at FP16 precision (~36 GB).
Apriel-15B-type6-e5-max-1e4-alpha0_25 vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about Apriel-15B-type6-e5-max-1e4-alpha0_25
Is Apriel-15B-type6-e5-max-1e4-alpha0_25 free to use?
Apriel-15B-type6-e5-max-1e4-alpha0_25 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 Apriel-15B-type6-e5-max-1e4-alpha0_25 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 Apriel-15B-type6-e5-max-1e4-alpha0_25 need?
Approximately 9 GB at Q4 quantisation, or 36 GB at full FP16 precision. Fits on a single 24GB consumer GPU.
Can I run Apriel-15B-type6-e5-max-1e4-alpha0_25 locally?
Yes. Apriel-15B-type6-e5-max-1e4-alpha0_25 is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is Apriel-15B-type6-e5-max-1e4-alpha0_25 best at?
Apriel-15B-type6-e5-max-1e4-alpha0_25 is well-suited to text generation.
How do I use Apriel-15B-type6-e5-max-1e4-alpha0_25 in osFoundry?
Paste your yufeng1 API key in the key dialog (or deploy the open weights for self-hostable models), assign Apriel-15B-type6-e5-max-1e4-alpha0_25 to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by yufeng1 on April 27, 2026. Source: https://huggingface.co/yufeng1/Apriel-15B-type6-e5-max-1e4-alpha0_25