Evolla-10B-hf
Evolla-10B-hf (westlake-repl, 2025) is a 10 billion parameter chat model. Evolla-10B-hf is an open-weights chat model with roughly 10 billion parameters.
by westlake-repl · 10B parameters
Best for
- low-latency chat and routing
- request routing and triage
- text classification
Ways to use Evolla-10B-hf in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your westlake-repl API key. osFoundry discovers Evolla-10B-hf 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
Evolla-10B-hf 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 Evolla-10B-hf
Evolla-10B-hf runs on a single 16GB consumer GPU (~6 GB VRAM with KV-cache headroom). Full-precision inference fits on a single H100 80GB at FP16 precision (~24 GB).
Evolla-10B-hf vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about Evolla-10B-hf
Is Evolla-10B-hf free to use?
Evolla-10B-hf 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 Evolla-10B-hf 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 Evolla-10B-hf need?
Approximately 6 GB at Q4 quantisation, or 24 GB at full FP16 precision. Fits on a single 24GB consumer GPU.
Can I run Evolla-10B-hf locally?
Yes. Evolla-10B-hf is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is Evolla-10B-hf best at?
Evolla-10B-hf is well-suited to low-latency chat and routing, request routing and triage, text classification.
How do I use Evolla-10B-hf in osFoundry?
Paste your westlake-repl API key in the key dialog (or deploy the open weights for self-hostable models), assign Evolla-10B-hf to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by westlake-repl on February 14, 2025. Source: https://huggingface.co/westlake-repl/Evolla-10B-hf