SFT_Qwen2.5-3B-Instruct_olympiads
Released by xw1234gan in 2026, SFT_Qwen2.5-3B-Instruct_olympiads is a 3 billion parameter chat model. SFT_Qwen2.5-3B-Instruct_olympiads is an open-weights chat model with roughly 3 billion parameters.
by xw1234gan · 3B parameters
Best for
Ways to use SFT_Qwen2.5-3B-Instruct_olympiads in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your xw1234gan API key. osFoundry discovers SFT_Qwen2.5-3B-Instruct_olympiads 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
SFT_Qwen2.5-3B-Instruct_olympiads 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 SFT_Qwen2.5-3B-Instruct_olympiads
SFT_Qwen2.5-3B-Instruct_olympiads 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).
SFT_Qwen2.5-3B-Instruct_olympiads vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about SFT_Qwen2.5-3B-Instruct_olympiads
Is SFT_Qwen2.5-3B-Instruct_olympiads free to use?
SFT_Qwen2.5-3B-Instruct_olympiads 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 SFT_Qwen2.5-3B-Instruct_olympiads 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 SFT_Qwen2.5-3B-Instruct_olympiads need?
Approximately 2 GB at Q4 quantisation, or 8 GB at full FP16 precision. Fits on a single 24GB consumer GPU.
Can I run SFT_Qwen2.5-3B-Instruct_olympiads locally?
Yes. SFT_Qwen2.5-3B-Instruct_olympiads is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is SFT_Qwen2.5-3B-Instruct_olympiads best at?
SFT_Qwen2.5-3B-Instruct_olympiads is well-suited to text generation.
How do I use SFT_Qwen2.5-3B-Instruct_olympiads in osFoundry?
Paste your xw1234gan API key in the key dialog (or deploy the open weights for self-hostable models), assign SFT_Qwen2.5-3B-Instruct_olympiads to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by xw1234gan on April 24, 2026. Source: https://huggingface.co/xw1234gan/SFT_Qwen2.5-3B-Instruct_olympiads