clt-qwen3-1.7b-base-20k
clt-qwen3-1.7b-base-20k (bluelightai, 2025) is a 2 billion parameter embedding model. clt-qwen3-1.7b-base-20k is an open-weights embed model with roughly 2 billion parameters.
by bluelightai · 2B parameters
Best for
Ways to use clt-qwen3-1.7b-base-20k in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your bluelightai API key. osFoundry discovers clt-qwen3-1.7b-base-20k 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
clt-qwen3-1.7b-base-20k 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 clt-qwen3-1.7b-base-20k
clt-qwen3-1.7b-base-20k runs on a single 16GB consumer GPU (~2 GB VRAM with KV-cache headroom). Full-precision inference fits on a single H100 80GB at FP16 precision (~5 GB).
clt-qwen3-1.7b-base-20k vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about clt-qwen3-1.7b-base-20k
Is clt-qwen3-1.7b-base-20k free to use?
clt-qwen3-1.7b-base-20k 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 clt-qwen3-1.7b-base-20k 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 clt-qwen3-1.7b-base-20k need?
Approximately 2 GB at Q4 quantisation, or 5 GB at full FP16 precision. Fits on a single 24GB consumer GPU.
Can I run clt-qwen3-1.7b-base-20k locally?
Yes. clt-qwen3-1.7b-base-20k is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is clt-qwen3-1.7b-base-20k best at?
clt-qwen3-1.7b-base-20k is well-suited to feature extraction.
How do I use clt-qwen3-1.7b-base-20k in osFoundry?
Paste your bluelightai API key in the key dialog (or deploy the open weights for self-hostable models), assign clt-qwen3-1.7b-base-20k to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by bluelightai on November 26, 2025. Source: https://huggingface.co/bluelightai/clt-qwen3-1.7b-base-20k