Deepseek-Coder-V2-Lite-13B-Instruct-sft-math7k
Released by HectorHe in 2025, Deepseek-Coder-V2-Lite-13B-Instruct-sft-math7k is a 13 billion parameter chat model. Deepseek-Coder-V2-Lite-13B-Instruct-sft-math7k is an open-weights chat model with roughly 13 billion parameters.
by HectorHe · 13B parameters
Best for
Ways to use Deepseek-Coder-V2-Lite-13B-Instruct-sft-math7k in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your HectorHe API key. osFoundry discovers Deepseek-Coder-V2-Lite-13B-Instruct-sft-math7k 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
Deepseek-Coder-V2-Lite-13B-Instruct-sft-math7k 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 Deepseek-Coder-V2-Lite-13B-Instruct-sft-math7k
Deepseek-Coder-V2-Lite-13B-Instruct-sft-math7k 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).
Deepseek-Coder-V2-Lite-13B-Instruct-sft-math7k vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about Deepseek-Coder-V2-Lite-13B-Instruct-sft-math7k
Is Deepseek-Coder-V2-Lite-13B-Instruct-sft-math7k free to use?
Deepseek-Coder-V2-Lite-13B-Instruct-sft-math7k 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 Deepseek-Coder-V2-Lite-13B-Instruct-sft-math7k 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 Deepseek-Coder-V2-Lite-13B-Instruct-sft-math7k need?
Approximately 8 GB at Q4 quantisation, or 32 GB at full FP16 precision. Fits on a single 24GB consumer GPU.
Can I run Deepseek-Coder-V2-Lite-13B-Instruct-sft-math7k locally?
Yes. Deepseek-Coder-V2-Lite-13B-Instruct-sft-math7k is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is Deepseek-Coder-V2-Lite-13B-Instruct-sft-math7k best at?
Deepseek-Coder-V2-Lite-13B-Instruct-sft-math7k is well-suited to text generation.
How do I use Deepseek-Coder-V2-Lite-13B-Instruct-sft-math7k in osFoundry?
Paste your HectorHe API key in the key dialog (or deploy the open weights for self-hostable models), assign Deepseek-Coder-V2-Lite-13B-Instruct-sft-math7k to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by HectorHe on August 13, 2025. Source: https://huggingface.co/HectorHe/Deepseek-Coder-V2-Lite-13B-Instruct-sft-math7k