llm-llama32-3b-paradigm-a-prime-r16-sft-stage1
dancinlab's llm-llama32-3b-paradigm-a-prime-r16-sft-stage1 packs 3 billion parameters into a chat model. llm-llama32-3b-paradigm-a-prime-r16-sft-stage1 is an open-weights chat model with roughly 3 billion parameters.
by dancinlab · 3B parameters
Best for
- low-latency chat and routing
- request routing and triage
- text classification
Ways to use llm-llama32-3b-paradigm-a-prime-r16-sft-stage1 in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your dancinlab API key. osFoundry discovers llm-llama32-3b-paradigm-a-prime-r16-sft-stage1 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
llm-llama32-3b-paradigm-a-prime-r16-sft-stage1 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 llm-llama32-3b-paradigm-a-prime-r16-sft-stage1
llm-llama32-3b-paradigm-a-prime-r16-sft-stage1 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).
llm-llama32-3b-paradigm-a-prime-r16-sft-stage1 vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about llm-llama32-3b-paradigm-a-prime-r16-sft-stage1
Is llm-llama32-3b-paradigm-a-prime-r16-sft-stage1 free to use?
llm-llama32-3b-paradigm-a-prime-r16-sft-stage1 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 llm-llama32-3b-paradigm-a-prime-r16-sft-stage1 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 llm-llama32-3b-paradigm-a-prime-r16-sft-stage1 need?
Approximately 2 GB at Q4 quantisation, or 8 GB at full FP16 precision. Fits on a single 24GB consumer GPU.
Can I run llm-llama32-3b-paradigm-a-prime-r16-sft-stage1 locally?
Yes. llm-llama32-3b-paradigm-a-prime-r16-sft-stage1 is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is llm-llama32-3b-paradigm-a-prime-r16-sft-stage1 best at?
llm-llama32-3b-paradigm-a-prime-r16-sft-stage1 is well-suited to low-latency chat and routing, request routing and triage, text classification.
How do I use llm-llama32-3b-paradigm-a-prime-r16-sft-stage1 in osFoundry?
Paste your dancinlab API key in the key dialog (or deploy the open weights for self-hostable models), assign llm-llama32-3b-paradigm-a-prime-r16-sft-stage1 to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by dancinlab on May 4, 2026. Source: https://huggingface.co/dancinlab/llm-llama32-3b-paradigm-a-prime-r16-sft-stage1