Llama-3.2-3B-Instruct_coding
Released by MergeBench in 2025, Llama-3.2-3B-Instruct_coding is a 3 billion parameter chat model. Llama-3.2-3B-Instruct_coding is an open-weights chat model with roughly 3 billion parameters.
by MergeBench · 3B parameters
Best for
Ways to use Llama-3.2-3B-Instruct_coding in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your MergeBench API key. osFoundry discovers Llama-3.2-3B-Instruct_coding 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
Llama-3.2-3B-Instruct_coding 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 Llama-3.2-3B-Instruct_coding
Llama-3.2-3B-Instruct_coding 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).
Llama-3.2-3B-Instruct_coding vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about Llama-3.2-3B-Instruct_coding
Is Llama-3.2-3B-Instruct_coding free to use?
Llama-3.2-3B-Instruct_coding 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 Llama-3.2-3B-Instruct_coding 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 Llama-3.2-3B-Instruct_coding need?
Approximately 2 GB at Q4 quantisation, or 8 GB at full FP16 precision. Fits on a single 24GB consumer GPU.
Can I run Llama-3.2-3B-Instruct_coding locally?
Yes. Llama-3.2-3B-Instruct_coding is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is Llama-3.2-3B-Instruct_coding best at?
Llama-3.2-3B-Instruct_coding is well-suited to text generation.
How do I use Llama-3.2-3B-Instruct_coding in osFoundry?
Paste your MergeBench API key in the key dialog (or deploy the open weights for self-hostable models), assign Llama-3.2-3B-Instruct_coding to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by MergeBench on May 14, 2025. Source: https://huggingface.co/MergeBench/Llama-3.2-3B-Instruct_coding