arc-grpo-deepseek-r1-distill-qwen-1.5b-rajat-seed-42-G-4-new_merged
Built by rghosh8, arc-grpo-deepseek-r1-distill-qwen-1.5b-rajat-seed-42-G-4-new_merged is a 2 billion parameter chat model. arc-grpo-deepseek-r1-distill-qwen-1.5b-rajat-seed-42-G-4-new_merged is an open-weights chat model with roughly 2 billion parameters.
by rghosh8 · 2B parameters
Best for
- low-latency chat and routing
- request routing and triage
- text classification
Ways to use arc-grpo-deepseek-r1-distill-qwen-1.5b-rajat-seed-42-G-4-new_merged in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your rghosh8 API key. osFoundry discovers arc-grpo-deepseek-r1-distill-qwen-1.5b-rajat-seed-42-G-4-new_merged 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
arc-grpo-deepseek-r1-distill-qwen-1.5b-rajat-seed-42-G-4-new_merged 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 arc-grpo-deepseek-r1-distill-qwen-1.5b-rajat-seed-42-G-4-new_merged
arc-grpo-deepseek-r1-distill-qwen-1.5b-rajat-seed-42-G-4-new_merged 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).
arc-grpo-deepseek-r1-distill-qwen-1.5b-rajat-seed-42-G-4-new_merged vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about arc-grpo-deepseek-r1-distill-qwen-1.5b-rajat-seed-42-G-4-new_merged
Is arc-grpo-deepseek-r1-distill-qwen-1.5b-rajat-seed-42-G-4-new_merged free to use?
arc-grpo-deepseek-r1-distill-qwen-1.5b-rajat-seed-42-G-4-new_merged 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 arc-grpo-deepseek-r1-distill-qwen-1.5b-rajat-seed-42-G-4-new_merged 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 arc-grpo-deepseek-r1-distill-qwen-1.5b-rajat-seed-42-G-4-new_merged need?
Approximately 2 GB at Q4 quantisation, or 5 GB at full FP16 precision. Fits on a single 24GB consumer GPU.
Can I run arc-grpo-deepseek-r1-distill-qwen-1.5b-rajat-seed-42-G-4-new_merged locally?
Yes. arc-grpo-deepseek-r1-distill-qwen-1.5b-rajat-seed-42-G-4-new_merged is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is arc-grpo-deepseek-r1-distill-qwen-1.5b-rajat-seed-42-G-4-new_merged best at?
arc-grpo-deepseek-r1-distill-qwen-1.5b-rajat-seed-42-G-4-new_merged is well-suited to low-latency chat and routing, request routing and triage, text classification.
How do I use arc-grpo-deepseek-r1-distill-qwen-1.5b-rajat-seed-42-G-4-new_merged in osFoundry?
Paste your rghosh8 API key in the key dialog (or deploy the open weights for self-hostable models), assign arc-grpo-deepseek-r1-distill-qwen-1.5b-rajat-seed-42-G-4-new_merged to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by rghosh8 on April 12, 2026. Source: https://huggingface.co/rghosh8/arc-grpo-deepseek-r1-distill-qwen-1.5b-rajat-seed-42-G-4-new_merged