Llama-2-70b-chat-hf_FP8_MLPerf_V2
Llama-2-70b-chat-hf_FP8_MLPerf_V2 (amd, 2025) is a 70 billion parameter chat model. Llama-2-70b-chat-hf_FP8_MLPerf_V2 is an open-weights chat model with roughly 70 billion parameters.
by amd · 70B parameters
Best for
- complex multi-step reasoning
- agent orchestration with tool use
- long-document analysis and summarisation
Ways to use Llama-2-70b-chat-hf_FP8_MLPerf_V2 in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your amd API key. osFoundry discovers Llama-2-70b-chat-hf_FP8_MLPerf_V2 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
Llama-2-70b-chat-hf_FP8_MLPerf_V2 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 Llama-2-70b-chat-hf_FP8_MLPerf_V2
Llama-2-70b-chat-hf_FP8_MLPerf_V2 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).
Llama-2-70b-chat-hf_FP8_MLPerf_V2 vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about Llama-2-70b-chat-hf_FP8_MLPerf_V2
Is Llama-2-70b-chat-hf_FP8_MLPerf_V2 free to use?
Llama-2-70b-chat-hf_FP8_MLPerf_V2 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 Llama-2-70b-chat-hf_FP8_MLPerf_V2 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 Llama-2-70b-chat-hf_FP8_MLPerf_V2 need?
Approximately 42 GB at Q4 quantisation, or 168 GB at full FP16 precision. Fits on a single A100/H100 80GB.
Can I run Llama-2-70b-chat-hf_FP8_MLPerf_V2 locally?
Yes. Llama-2-70b-chat-hf_FP8_MLPerf_V2 is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is Llama-2-70b-chat-hf_FP8_MLPerf_V2 best at?
Llama-2-70b-chat-hf_FP8_MLPerf_V2 is well-suited to complex multi-step reasoning, agent orchestration with tool use, long-document analysis and summarisation.
How do I use Llama-2-70b-chat-hf_FP8_MLPerf_V2 in osFoundry?
Paste your amd API key in the key dialog (or deploy the open weights for self-hostable models), assign Llama-2-70b-chat-hf_FP8_MLPerf_V2 to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by amd on January 7, 2025. Source: https://huggingface.co/amd/Llama-2-70b-chat-hf_FP8_MLPerf_V2