deepseek-r1-distill-llama-70b-awq
casperhansen's deepseek-r1-distill-llama-70b-awq packs 70 billion parameters into a chat model. deepseek-r1-distill-llama-70b-awq is an open-weights chat model with roughly 70 billion parameters.
by casperhansen · 70B parameters
Best for
- complex multi-step reasoning
- agent orchestration with tool use
- long-document analysis and summarisation
Ways to use deepseek-r1-distill-llama-70b-awq in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your casperhansen API key. osFoundry discovers deepseek-r1-distill-llama-70b-awq 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-r1-distill-llama-70b-awq 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-r1-distill-llama-70b-awq
deepseek-r1-distill-llama-70b-awq runs on a single A100 80GB or H100 80GB at Q4 quantisation (~42 GB VRAM with KV-cache headroom). Full-precision inference requires multiple H100/H200 GPUs at FP16 (~168 GB).
deepseek-r1-distill-llama-70b-awq vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about deepseek-r1-distill-llama-70b-awq
Is deepseek-r1-distill-llama-70b-awq free to use?
deepseek-r1-distill-llama-70b-awq 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-r1-distill-llama-70b-awq 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-r1-distill-llama-70b-awq need?
Approximately 42 GB at Q4 quantisation, or 168 GB at full FP16 precision. Fits on a single A100/H100 80GB.
Can I run deepseek-r1-distill-llama-70b-awq locally?
Yes. deepseek-r1-distill-llama-70b-awq is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is deepseek-r1-distill-llama-70b-awq best at?
deepseek-r1-distill-llama-70b-awq is well-suited to complex multi-step reasoning, agent orchestration with tool use, long-document analysis and summarisation.
How do I use deepseek-r1-distill-llama-70b-awq in osFoundry?
Paste your casperhansen API key in the key dialog (or deploy the open weights for self-hostable models), assign deepseek-r1-distill-llama-70b-awq to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by casperhansen on January 20, 2025. Source: https://huggingface.co/casperhansen/deepseek-r1-distill-llama-70b-awq