Falcon3-10B-Base-1.58bit-prequantized
tiiuae's Falcon3-10B-Base-1.58bit-prequantized packs 10 billion parameters into a chat model. Falcon3-10B-Base-1.58bit-prequantized is an open-weights chat model with roughly 10 billion parameters.
by tiiuae · 10B parameters
Best for
Ways to use Falcon3-10B-Base-1.58bit-prequantized in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your tiiuae API key. osFoundry discovers Falcon3-10B-Base-1.58bit-prequantized 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
Falcon3-10B-Base-1.58bit-prequantized 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 Falcon3-10B-Base-1.58bit-prequantized
Falcon3-10B-Base-1.58bit-prequantized runs on a single 16GB consumer GPU (~6 GB VRAM with KV-cache headroom). Full-precision inference fits on a single H100 80GB at FP16 precision (~24 GB).
Falcon3-10B-Base-1.58bit-prequantized vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about Falcon3-10B-Base-1.58bit-prequantized
Is Falcon3-10B-Base-1.58bit-prequantized free to use?
Falcon3-10B-Base-1.58bit-prequantized 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 Falcon3-10B-Base-1.58bit-prequantized 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 Falcon3-10B-Base-1.58bit-prequantized need?
Approximately 6 GB at Q4 quantisation, or 24 GB at full FP16 precision. Fits on a single 24GB consumer GPU.
Can I run Falcon3-10B-Base-1.58bit-prequantized locally?
Yes. Falcon3-10B-Base-1.58bit-prequantized is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is Falcon3-10B-Base-1.58bit-prequantized best at?
Falcon3-10B-Base-1.58bit-prequantized is well-suited to text generation.
How do I use Falcon3-10B-Base-1.58bit-prequantized in osFoundry?
Paste your tiiuae API key in the key dialog (or deploy the open weights for self-hostable models), assign Falcon3-10B-Base-1.58bit-prequantized to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by tiiuae on April 30, 2026. Source: https://huggingface.co/tiiuae/Falcon3-10B-Base-1.58bit-prequantized