cd /news/large-language-models/meta-llama-3-8b-instruct-retired · home › topics › large-language-models › article
[ARTICLE · art-105515] src=llmstatus.ai ↗ pub= topic=large-language-models verified=true sentiment=· neutral

Meta-Llama-3-8B-Instruct retired

Microsoft retired Meta-Llama-3-8B-Instruct on Azure AI Foundry, removing the serverless deployment and delisting the model from models.dev's Azure catalog in August 2026. The model, released on 2024-04-18 with an 8k context window and 2k max output, had no announced retirement date. The retirement affects developers using the model via Azure-hosted deployments.

read1 min views9 publishedAug 19, 2026
Meta-Llama-3-8B-Instruct retired
Image: Llmstatus (auto-discovered)

MF✕ Retired

Microsoft · meta-llama-3-8b-instruct Retired on Azure AI Foundry (azure-hosted deployment). Llama-3.0 serverless retirement; row since purged from the schedule doc, exact date no longer published. Delisted from models.dev's azure catalog 2026-08.

Provider statement →Released2024-04-18 Retiresno announced date

llamatext8k context2k max out

also matches:

`meta-llama-3-8b-instruct`

`microsoft/meta-llama-3-8b-instruct`

[provider announcement →](https://raw.githubusercontent.com/MicrosoftDocs/azure-ai-docs/main/articles/ai-foundry/openai/includes/retirement/models.md)

Does your code call Meta-Llama-3-8B-Instruct?

$ curl -fsSL https://llmstatus.ai/install.sh | bash

Then mm status

in any repo — it finds every model you use and flags the ones on a clock. No account, nothing uploaded.

Get alerted before it retires →

source & further reading
llmstatus.ai — original article New model: Qwen3.8 Flash (Alibaba (Qwen)) GLM-5.3-Flash deprecated, retires 2098-12-31 New model: GLM-5.2 (Mistral AI)
── more in #large-language-models 4 stories · sorted by recency
── more on @microsoft 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
→ Live at https://your-agent.zahid.host ✓
Get free account → Pricing
from €0/mo · no card required
LIVE [news/meta-llama-3-8b-inst…] indexed:0 read:1min 2026-08-19 · —