Falcon-H1-34B-Instruct-GPTQ-Int4
Falcon-H1-34B-Instruct-GPTQ-Int4 is a 34 billion parameter chat model from tiiuae, released May 12, 2025. Falcon-H1-34B-Instruct-GPTQ-Int4 is an open-weights chat model with roughly 34 billion parameters.
by tiiuae · 34B parameters
Best for
Ways to use Falcon-H1-34B-Instruct-GPTQ-Int4 in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your tiiuae API key. osFoundry discovers Falcon-H1-34B-Instruct-GPTQ-Int4 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
Falcon-H1-34B-Instruct-GPTQ-Int4 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 Falcon-H1-34B-Instruct-GPTQ-Int4
Falcon-H1-34B-Instruct-GPTQ-Int4 runs on a 24GB consumer or workstation GPU (~21 GB VRAM with KV-cache headroom). Full-precision inference requires an H200 141GB or 2x A100 80GB at FP16 (~82 GB).
Falcon-H1-34B-Instruct-GPTQ-Int4 vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about Falcon-H1-34B-Instruct-GPTQ-Int4
Is Falcon-H1-34B-Instruct-GPTQ-Int4 free to use?
Falcon-H1-34B-Instruct-GPTQ-Int4 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 Falcon-H1-34B-Instruct-GPTQ-Int4 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 Falcon-H1-34B-Instruct-GPTQ-Int4 need?
Approximately 21 GB at Q4 quantisation, or 82 GB at full FP16 precision. Fits on a single 24GB consumer GPU.
Can I run Falcon-H1-34B-Instruct-GPTQ-Int4 locally?
Yes. Falcon-H1-34B-Instruct-GPTQ-Int4 is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is Falcon-H1-34B-Instruct-GPTQ-Int4 best at?
Falcon-H1-34B-Instruct-GPTQ-Int4 is well-suited to text generation.
How do I use Falcon-H1-34B-Instruct-GPTQ-Int4 in osFoundry?
Paste your tiiuae API key in the key dialog (or deploy the open weights for self-hostable models), assign Falcon-H1-34B-Instruct-GPTQ-Int4 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 May 12, 2025. Source: https://huggingface.co/tiiuae/Falcon-H1-34B-Instruct-GPTQ-Int4