science_1bmix_bt4b-4c5dce14-not_easy_1e-4_400
Released by graf in 2026, science_1bmix_bt4b-4c5dce14-not_easy_1e-4_400 is a 4 billion parameter chat model. science_1bmix_bt4b-4c5dce14-not_easy_1e-4_400 is an open-weights chat model with roughly 4 billion parameters.
by graf · 4B parameters
Best for
- low-latency chat and routing
- request routing and triage
- text classification
Ways to use science_1bmix_bt4b-4c5dce14-not_easy_1e-4_400 in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your graf API key. osFoundry discovers science_1bmix_bt4b-4c5dce14-not_easy_1e-4_400 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
science_1bmix_bt4b-4c5dce14-not_easy_1e-4_400 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 science_1bmix_bt4b-4c5dce14-not_easy_1e-4_400
science_1bmix_bt4b-4c5dce14-not_easy_1e-4_400 runs on a single 16GB consumer GPU (~3 GB VRAM with KV-cache headroom). Full-precision inference fits on a single H100 80GB at FP16 precision (~10 GB).
science_1bmix_bt4b-4c5dce14-not_easy_1e-4_400 vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about science_1bmix_bt4b-4c5dce14-not_easy_1e-4_400
Is science_1bmix_bt4b-4c5dce14-not_easy_1e-4_400 free to use?
science_1bmix_bt4b-4c5dce14-not_easy_1e-4_400 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 science_1bmix_bt4b-4c5dce14-not_easy_1e-4_400 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 science_1bmix_bt4b-4c5dce14-not_easy_1e-4_400 need?
Approximately 3 GB at Q4 quantisation, or 10 GB at full FP16 precision. Fits on a single 24GB consumer GPU.
Can I run science_1bmix_bt4b-4c5dce14-not_easy_1e-4_400 locally?
Yes. science_1bmix_bt4b-4c5dce14-not_easy_1e-4_400 is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is science_1bmix_bt4b-4c5dce14-not_easy_1e-4_400 best at?
science_1bmix_bt4b-4c5dce14-not_easy_1e-4_400 is well-suited to low-latency chat and routing, request routing and triage, text classification.
How do I use science_1bmix_bt4b-4c5dce14-not_easy_1e-4_400 in osFoundry?
Paste your graf API key in the key dialog (or deploy the open weights for self-hostable models), assign science_1bmix_bt4b-4c5dce14-not_easy_1e-4_400 to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by graf on April 25, 2026. Source: https://huggingface.co/graf/science_1bmix_bt4b-4c5dce14-not_easy_1e-4_400