SIP-jmed-llm-3-8x13b-AC-32k-instruct
Built by SIP-med-LLM, SIP-jmed-llm-3-8x13b-AC-32k-instruct is a 13 billion parameter chat model. SIP-jmed-llm-3-8x13b-AC-32k-instruct is an open-weights chat model with roughly 13 billion parameters.
by SIP-med-LLM · 13B parameters
Best for
- low-latency chat and routing
- request routing and triage
- text classification
Ways to use SIP-jmed-llm-3-8x13b-AC-32k-instruct in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your SIP-med-LLM API key. osFoundry discovers SIP-jmed-llm-3-8x13b-AC-32k-instruct 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
SIP-jmed-llm-3-8x13b-AC-32k-instruct 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 SIP-jmed-llm-3-8x13b-AC-32k-instruct
SIP-jmed-llm-3-8x13b-AC-32k-instruct runs on a single 16GB consumer GPU (~8 GB VRAM with KV-cache headroom). Full-precision inference fits on a single H100 80GB at FP16 precision (~32 GB).
SIP-jmed-llm-3-8x13b-AC-32k-instruct vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about SIP-jmed-llm-3-8x13b-AC-32k-instruct
Is SIP-jmed-llm-3-8x13b-AC-32k-instruct free to use?
SIP-jmed-llm-3-8x13b-AC-32k-instruct 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 SIP-jmed-llm-3-8x13b-AC-32k-instruct 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 SIP-jmed-llm-3-8x13b-AC-32k-instruct need?
Approximately 8 GB at Q4 quantisation, or 32 GB at full FP16 precision. Fits on a single 24GB consumer GPU.
Can I run SIP-jmed-llm-3-8x13b-AC-32k-instruct locally?
Yes. SIP-jmed-llm-3-8x13b-AC-32k-instruct is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is SIP-jmed-llm-3-8x13b-AC-32k-instruct best at?
SIP-jmed-llm-3-8x13b-AC-32k-instruct is well-suited to low-latency chat and routing, request routing and triage, text classification.
How do I use SIP-jmed-llm-3-8x13b-AC-32k-instruct in osFoundry?
Paste your SIP-med-LLM API key in the key dialog (or deploy the open weights for self-hostable models), assign SIP-jmed-llm-3-8x13b-AC-32k-instruct to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by SIP-med-LLM on October 30, 2025. Source: https://huggingface.co/SIP-med-LLM/SIP-jmed-llm-3-8x13b-AC-32k-instruct