blood-donation-llama32-3b-merged-16bit
Released by HMkumbo in 2026, blood-donation-llama32-3b-merged-16bit is a 3 billion parameter chat model. blood-donation-llama32-3b-merged-16bit is an open-weights chat model with roughly 3 billion parameters.
by HMkumbo · 3B parameters
Best for
Ways to use blood-donation-llama32-3b-merged-16bit in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your HMkumbo API key. osFoundry discovers blood-donation-llama32-3b-merged-16bit 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
blood-donation-llama32-3b-merged-16bit 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 blood-donation-llama32-3b-merged-16bit
blood-donation-llama32-3b-merged-16bit 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).
blood-donation-llama32-3b-merged-16bit vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about blood-donation-llama32-3b-merged-16bit
Is blood-donation-llama32-3b-merged-16bit free to use?
blood-donation-llama32-3b-merged-16bit 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 blood-donation-llama32-3b-merged-16bit 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 blood-donation-llama32-3b-merged-16bit need?
Approximately 2 GB at Q4 quantisation, or 8 GB at full FP16 precision. Fits on a single 24GB consumer GPU.
Can I run blood-donation-llama32-3b-merged-16bit locally?
Yes. blood-donation-llama32-3b-merged-16bit is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is blood-donation-llama32-3b-merged-16bit best at?
blood-donation-llama32-3b-merged-16bit is well-suited to text generation.
How do I use blood-donation-llama32-3b-merged-16bit in osFoundry?
Paste your HMkumbo API key in the key dialog (or deploy the open weights for self-hostable models), assign blood-donation-llama32-3b-merged-16bit to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by HMkumbo on April 17, 2026. Source: https://huggingface.co/HMkumbo/blood-donation-llama32-3b-merged-16bit