open-sci-ref-v0.02-1.7b-dclm-300B-4096-longsft_16k
ali-elganzory's open-sci-ref-v0.02-1.7b-dclm-300B-4096-longsft_16k packs 2 billion parameters into a chat model. open-sci-ref-v0.02-1.7b-dclm-300B-4096-longsft_16k is an open-weights chat model with roughly 2 billion parameters.
by ali-elganzory · 2B parameters
Best for
Ways to use open-sci-ref-v0.02-1.7b-dclm-300B-4096-longsft_16k in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your ali-elganzory API key. osFoundry discovers open-sci-ref-v0.02-1.7b-dclm-300B-4096-longsft_16k 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
open-sci-ref-v0.02-1.7b-dclm-300B-4096-longsft_16k 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 open-sci-ref-v0.02-1.7b-dclm-300B-4096-longsft_16k
open-sci-ref-v0.02-1.7b-dclm-300B-4096-longsft_16k 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).
open-sci-ref-v0.02-1.7b-dclm-300B-4096-longsft_16k vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about open-sci-ref-v0.02-1.7b-dclm-300B-4096-longsft_16k
Is open-sci-ref-v0.02-1.7b-dclm-300B-4096-longsft_16k free to use?
open-sci-ref-v0.02-1.7b-dclm-300B-4096-longsft_16k 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 open-sci-ref-v0.02-1.7b-dclm-300B-4096-longsft_16k 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 open-sci-ref-v0.02-1.7b-dclm-300B-4096-longsft_16k need?
Approximately 2 GB at Q4 quantisation, or 5 GB at full FP16 precision. Fits on a single 24GB consumer GPU.
Can I run open-sci-ref-v0.02-1.7b-dclm-300B-4096-longsft_16k locally?
Yes. open-sci-ref-v0.02-1.7b-dclm-300B-4096-longsft_16k is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is open-sci-ref-v0.02-1.7b-dclm-300B-4096-longsft_16k best at?
open-sci-ref-v0.02-1.7b-dclm-300B-4096-longsft_16k is well-suited to text generation.
How do I use open-sci-ref-v0.02-1.7b-dclm-300B-4096-longsft_16k in osFoundry?
Paste your ali-elganzory API key in the key dialog (or deploy the open weights for self-hostable models), assign open-sci-ref-v0.02-1.7b-dclm-300B-4096-longsft_16k to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by ali-elganzory on April 17, 2026. Source: https://huggingface.co/ali-elganzory/open-sci-ref-v0.02-1.7b-dclm-300B-4096-longsft_16k