qwen25-math-1.5b-prm-lora-step-continuation-5epochs
qwen25-math-1.5b-prm-lora-step-continuation-5epochs is a 2 billion parameter embedding model from rediska0123, released March 19, 2026. qwen25-math-1.5b-prm-lora-step-continuation-5epochs is an open-weights embed model with roughly 2 billion parameters.
by rediska0123 · 2B parameters
Best for
Ways to use qwen25-math-1.5b-prm-lora-step-continuation-5epochs in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your rediska0123 API key. osFoundry discovers qwen25-math-1.5b-prm-lora-step-continuation-5epochs 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
qwen25-math-1.5b-prm-lora-step-continuation-5epochs 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 qwen25-math-1.5b-prm-lora-step-continuation-5epochs
qwen25-math-1.5b-prm-lora-step-continuation-5epochs 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 (~5 GB).
qwen25-math-1.5b-prm-lora-step-continuation-5epochs vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about qwen25-math-1.5b-prm-lora-step-continuation-5epochs
Is qwen25-math-1.5b-prm-lora-step-continuation-5epochs free to use?
qwen25-math-1.5b-prm-lora-step-continuation-5epochs 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 qwen25-math-1.5b-prm-lora-step-continuation-5epochs 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 qwen25-math-1.5b-prm-lora-step-continuation-5epochs need?
Approximately 2 GB at Q4 quantisation, or 5 GB at full FP16 precision. Fits on a single 24GB consumer GPU.
Can I run qwen25-math-1.5b-prm-lora-step-continuation-5epochs locally?
Yes. qwen25-math-1.5b-prm-lora-step-continuation-5epochs is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is qwen25-math-1.5b-prm-lora-step-continuation-5epochs best at?
qwen25-math-1.5b-prm-lora-step-continuation-5epochs is well-suited to feature extraction.
How do I use qwen25-math-1.5b-prm-lora-step-continuation-5epochs in osFoundry?
Paste your rediska0123 API key in the key dialog (or deploy the open weights for self-hostable models), assign qwen25-math-1.5b-prm-lora-step-continuation-5epochs to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by rediska0123 on March 19, 2026. Source: https://huggingface.co/rediska0123/qwen25-math-1.5b-prm-lora-step-continuation-5epochs