evolm-1B-160BT-cpt-FM30BT
Released by zhenting in 2025, evolm-1B-160BT-cpt-FM30BT is a 1 billion parameter chat model. evolm-1B-160BT-cpt-FM30BT is an open-weights chat model with roughly 1 billion parameters.
by zhenting · 1B parameters
Best for
- low-latency chat and routing
- request routing and triage
- text classification
Ways to use evolm-1B-160BT-cpt-FM30BT in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your zhenting API key. osFoundry discovers evolm-1B-160BT-cpt-FM30BT 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
evolm-1B-160BT-cpt-FM30BT 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 evolm-1B-160BT-cpt-FM30BT
evolm-1B-160BT-cpt-FM30BT runs on a single 16GB consumer GPU (~1 GB VRAM with KV-cache headroom). Full-precision inference fits on a single H100 80GB at FP16 precision (~3 GB).
evolm-1B-160BT-cpt-FM30BT vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about evolm-1B-160BT-cpt-FM30BT
Is evolm-1B-160BT-cpt-FM30BT free to use?
evolm-1B-160BT-cpt-FM30BT 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 evolm-1B-160BT-cpt-FM30BT 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 evolm-1B-160BT-cpt-FM30BT need?
Approximately 1 GB at Q4 quantisation, or 3 GB at full FP16 precision. Fits on a single 24GB consumer GPU.
Can I run evolm-1B-160BT-cpt-FM30BT locally?
Yes. evolm-1B-160BT-cpt-FM30BT is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is evolm-1B-160BT-cpt-FM30BT best at?
evolm-1B-160BT-cpt-FM30BT is well-suited to low-latency chat and routing, request routing and triage, text classification.
How do I use evolm-1B-160BT-cpt-FM30BT in osFoundry?
Paste your zhenting API key in the key dialog (or deploy the open weights for self-hostable models), assign evolm-1B-160BT-cpt-FM30BT to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by zhenting on February 14, 2025. Source: https://huggingface.co/zhenting/evolm-1B-160BT-cpt-FM30BT