llama32-3b-pruned-25-percent
llama32-3b-pruned-25-percent is a 3 billion parameter chat model from KobeBeef67, released April 16, 2026. llama32-3b-pruned-25-percent is an open-weights chat model with roughly 3 billion parameters.
by KobeBeef67 · 3B parameters
Best for
Ways to use llama32-3b-pruned-25-percent in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your KobeBeef67 API key. osFoundry discovers llama32-3b-pruned-25-percent 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
llama32-3b-pruned-25-percent 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 llama32-3b-pruned-25-percent
llama32-3b-pruned-25-percent 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 (~8 GB).
llama32-3b-pruned-25-percent vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about llama32-3b-pruned-25-percent
Is llama32-3b-pruned-25-percent free to use?
llama32-3b-pruned-25-percent 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 llama32-3b-pruned-25-percent 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 llama32-3b-pruned-25-percent need?
Approximately 2 GB at Q4 quantisation, or 8 GB at full FP16 precision. Fits on a single 24GB consumer GPU.
Can I run llama32-3b-pruned-25-percent locally?
Yes. llama32-3b-pruned-25-percent is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is llama32-3b-pruned-25-percent best at?
llama32-3b-pruned-25-percent is well-suited to text generation.
How do I use llama32-3b-pruned-25-percent in osFoundry?
Paste your KobeBeef67 API key in the key dialog (or deploy the open weights for self-hostable models), assign llama32-3b-pruned-25-percent to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by KobeBeef67 on April 16, 2026. Source: https://huggingface.co/KobeBeef67/llama32-3b-pruned-25-percent