bigstral-12b-32k
bigstral-12b-32k is a 12 billion parameter chat model from abacusai, released March 6, 2024. bigstral-12b-32k is an open-weights chat model with roughly 12 billion parameters.
by abacusai · 12B parameters
Best for
Ways to use bigstral-12b-32k in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your abacusai API key. osFoundry discovers bigstral-12b-32k 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
bigstral-12b-32k 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 bigstral-12b-32k
bigstral-12b-32k runs on a single 16GB consumer GPU (~8 GB VRAM with KV-cache headroom). Full-precision inference fits on a single H100 80GB at FP16 precision (~29 GB).
bigstral-12b-32k vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about bigstral-12b-32k
Is bigstral-12b-32k free to use?
bigstral-12b-32k 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 bigstral-12b-32k 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 bigstral-12b-32k need?
Approximately 8 GB at Q4 quantisation, or 29 GB at full FP16 precision. Fits on a single 24GB consumer GPU.
Can I run bigstral-12b-32k locally?
Yes. bigstral-12b-32k is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is bigstral-12b-32k best at?
bigstral-12b-32k is well-suited to text generation.
How do I use bigstral-12b-32k in osFoundry?
Paste your abacusai API key in the key dialog (or deploy the open weights for self-hostable models), assign bigstral-12b-32k to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by abacusai on March 6, 2024. Source: https://huggingface.co/abacusai/bigstral-12b-32k