P2-split5_only_answer_Qwen3-4B-Base_0505-bs64-epoch6-lr1e5
Built by Hyeongwon, P2-split5_only_answer_Qwen3-4B-Base_0505-bs64-epoch6-lr1e5 is a 4 billion parameter chat model. P2-split5_only_answer_Qwen3-4B-Base_0505-bs64-epoch6-lr1e5 is an open-weights chat model with roughly 4 billion parameters.
by Hyeongwon · 4B parameters
Best for
Ways to use P2-split5_only_answer_Qwen3-4B-Base_0505-bs64-epoch6-lr1e5 in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your Hyeongwon API key. osFoundry discovers P2-split5_only_answer_Qwen3-4B-Base_0505-bs64-epoch6-lr1e5 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
P2-split5_only_answer_Qwen3-4B-Base_0505-bs64-epoch6-lr1e5 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 P2-split5_only_answer_Qwen3-4B-Base_0505-bs64-epoch6-lr1e5
P2-split5_only_answer_Qwen3-4B-Base_0505-bs64-epoch6-lr1e5 runs on a single 16GB consumer GPU (~3 GB VRAM with KV-cache headroom). Full-precision inference fits on a single H100 80GB at FP16 precision (~10 GB).
P2-split5_only_answer_Qwen3-4B-Base_0505-bs64-epoch6-lr1e5 vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about P2-split5_only_answer_Qwen3-4B-Base_0505-bs64-epoch6-lr1e5
Is P2-split5_only_answer_Qwen3-4B-Base_0505-bs64-epoch6-lr1e5 free to use?
P2-split5_only_answer_Qwen3-4B-Base_0505-bs64-epoch6-lr1e5 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 P2-split5_only_answer_Qwen3-4B-Base_0505-bs64-epoch6-lr1e5 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 P2-split5_only_answer_Qwen3-4B-Base_0505-bs64-epoch6-lr1e5 need?
Approximately 3 GB at Q4 quantisation, or 10 GB at full FP16 precision. Fits on a single 24GB consumer GPU.
Can I run P2-split5_only_answer_Qwen3-4B-Base_0505-bs64-epoch6-lr1e5 locally?
Yes. P2-split5_only_answer_Qwen3-4B-Base_0505-bs64-epoch6-lr1e5 is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is P2-split5_only_answer_Qwen3-4B-Base_0505-bs64-epoch6-lr1e5 best at?
P2-split5_only_answer_Qwen3-4B-Base_0505-bs64-epoch6-lr1e5 is well-suited to text generation.
How do I use P2-split5_only_answer_Qwen3-4B-Base_0505-bs64-epoch6-lr1e5 in osFoundry?
Paste your Hyeongwon API key in the key dialog (or deploy the open weights for self-hostable models), assign P2-split5_only_answer_Qwen3-4B-Base_0505-bs64-epoch6-lr1e5 to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by Hyeongwon on May 5, 2026. Source: https://huggingface.co/Hyeongwon/P2-split5_only_answer_Qwen3-4B-Base_0505-bs64-epoch6-lr1e5