Llama-3.2-3B-Instruct_grpo_ppl_adv_rollout_8_resume_epoch10_20260429_004543_step232
Llama-3.2-3B-Instruct_grpo_ppl_adv_rollout_8_resume_epoch10_20260429_004543_step232 (parkjo, 2026) is a 3 billion parameter chat model. Llama-3.2-3B-Instruct_grpo_ppl_adv_rollout_8_resume_epoch10_20260429_004543_step232 is an open-weights chat model with roughly 3 billion parameters.
by parkjo · 3B parameters
Best for
- low-latency chat and routing
- request routing and triage
- text classification
Ways to use Llama-3.2-3B-Instruct_grpo_ppl_adv_rollout_8_resume_epoch10_20260429_004543_step232 in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your parkjo API key. osFoundry discovers Llama-3.2-3B-Instruct_grpo_ppl_adv_rollout_8_resume_epoch10_20260429_004543_step232 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_grpo_ppl_adv_rollout_8_resume_epoch10_20260429_004543_step232 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_grpo_ppl_adv_rollout_8_resume_epoch10_20260429_004543_step232
Llama-3.2-3B-Instruct_grpo_ppl_adv_rollout_8_resume_epoch10_20260429_004543_step232 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_grpo_ppl_adv_rollout_8_resume_epoch10_20260429_004543_step232 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_grpo_ppl_adv_rollout_8_resume_epoch10_20260429_004543_step232
Is Llama-3.2-3B-Instruct_grpo_ppl_adv_rollout_8_resume_epoch10_20260429_004543_step232 free to use?
Llama-3.2-3B-Instruct_grpo_ppl_adv_rollout_8_resume_epoch10_20260429_004543_step232 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_grpo_ppl_adv_rollout_8_resume_epoch10_20260429_004543_step232 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_grpo_ppl_adv_rollout_8_resume_epoch10_20260429_004543_step232 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_grpo_ppl_adv_rollout_8_resume_epoch10_20260429_004543_step232 locally?
Yes. Llama-3.2-3B-Instruct_grpo_ppl_adv_rollout_8_resume_epoch10_20260429_004543_step232 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_grpo_ppl_adv_rollout_8_resume_epoch10_20260429_004543_step232 best at?
Llama-3.2-3B-Instruct_grpo_ppl_adv_rollout_8_resume_epoch10_20260429_004543_step232 is well-suited to low-latency chat and routing, request routing and triage, text classification.
How do I use Llama-3.2-3B-Instruct_grpo_ppl_adv_rollout_8_resume_epoch10_20260429_004543_step232 in osFoundry?
Paste your parkjo API key in the key dialog (or deploy the open weights for self-hostable models), assign Llama-3.2-3B-Instruct_grpo_ppl_adv_rollout_8_resume_epoch10_20260429_004543_step232 to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by parkjo on May 12, 2026. Source: https://huggingface.co/parkjo/Llama-3.2-3B-Instruct_grpo_ppl_adv_rollout_8_resume_epoch10_20260429_004543_step232