Skip to content

Open-source platform for 3D AI agents. Turn text or a photo into a rigged, animated GLB avatar, give it an LLM brain, memory and a wallet, and embed it anywhere with one web component. Remote MCP server, x402 payments, Three.js, browser-native.

docs(nvidia): record the model-retirement forum post as live and link it from the model map

qhqf883b9a28eb8a
diff --git a/docs/nvidia-forum-model-retirement-post.md b/docs/nvidia-forum-model-retirement-post.md
index 6c5bbc036..09f2a1917 100644
--- a/docs/nvidia-forum-model-retirement-post.md
+++ b/docs/nvidia-forum-model-retirement-post.md
@@ -7,7 +7,8 @@ description: "Both models featured in our two earlier NVIDIA forum posts were re
tags: [nim, nemotron, llama]
links_in_body: 2, both to forums.developer.nvidia.com (our own earlier topics). No external hyperlinks; three.ws and repo paths are plain text on purpose.
images: 0
-status: draft, owner approval required before posting (external-channel gate in CLAUDE.md)
+status: posted 2026-09-21
+live: https://forums.developer.nvidia.com/t/nvidia-nim-model-retirements-what-a-410-gone-does-to-a-fallback-chain-and-how-we-survive-it-now/383950
---
# NVIDIA NIM model retirements: what a 410 Gone does to a fallback chain, and how we survive it now
diff --git a/docs/nvidia-models.md b/docs/nvidia-models.md
index 9ad1dec5d..29607fcc1 100644
--- a/docs/nvidia-models.md
+++ b/docs/nvidia-models.md
@@ -200,6 +200,7 @@ The free NVIDIA TTS lane: **Magpie multilingual on Riva**, selected by an NVCF `
- [NVIDIA Inception membership](/docs/nvidia-inception) - what membership adds on top of this free lane
- [The generator was never the hard part](/docs/nvidia-nemotron-spotlight) - our Nemotron Nano write-up, published on the NVIDIA Developer Forums
+- [NIM model retirements and the 410 that hides from a fallback chain](https://forums.developer.nvidia.com/t/nvidia-nim-model-retirements-what-a-410-gone-does-to-a-fallback-chain-and-how-we-survive-it-now/383950) - the forum post behind the 2026-09-10 re-pins on this page
- [Image-to-3D on NVIDIA L4 and Blackwell](https://three.ws/blog/image-to-3d-on-nvidia-l4-and-blackwell) - the self-hosted GPU fleet behind the paid lanes, and the two walls we hit moving to Blackwell
- [How Forge works](/docs/how-forge-works) - the /forge product this layer powers
- [REST API](/docs/api-reference) - the endpoints these models serve
diff --git a/docs/nvidia-visibility-map.md b/docs/nvidia-visibility-map.md
index 718d433dc..cc4ee178e 100644
--- a/docs/nvidia-visibility-map.md
+++ b/docs/nvidia-visibility-map.md
@@ -220,10 +220,11 @@ separate chance for a reshare.
## Technical publishing (the proven channel)
-Two forum posts, both live, both landed:
+Three forum posts, all live, all landed:
- [How Nemotron made three.ws text-to-3D pipeline usable](https://forums.developer.nvidia.com/t/how-nemotron-made-three-ws-text-to-3d-pipeline-usable/376445)
- [How three.ws translates a web app into 100 languages with NVIDIA NIM](https://forums.developer.nvidia.com/t/how-three-ws-translates-a-web-app-into-100-languages-with-nvidia-nim-an-llm-powered-i18n-pipeline/377379)
+- [NVIDIA NIM model retirements: what a 410 Gone does to a fallback chain](https://forums.developer.nvidia.com/t/nvidia-nim-model-retirements-what-a-410-gone-does-to-a-fallback-chain-and-how-we-survive-it-now/383950) (posted 2026-09-21 from [nvidia-forum-model-retirement-post.md](./nvidia-forum-model-retirement-post.md), written to the pattern below)
This is the only NVIDIA channel where we have a track record, it is self-serve,
and it feeds everything else: forum posts are what a Technical Blog pitch and a
@@ -231,8 +232,8 @@ GTC abstract are built on.
### What the approved posts have in common (read before drafting the next one)
-Three topics from the `nichxbt` account cleared moderation as of 2026-09-21: the
-two above and a CloudXR 6.2 support question, which drew an NVIDIA employee
+Three topics from the `nichxbt` account had cleared moderation as of 2026-09-21: the
+first two above and a CloudXR 6.2 support question, which drew an NVIDIA employee
reply the same day. We cannot see the forum's moderation settings, so this is
the pattern in what passed, plus the stock Discourse new-user defaults (two
links and one image per post, and an automatic hold once a new account keeps
@@ -285,7 +286,6 @@ when approved.
|---|---|
| [nvidia-forum-gpu-fleet-post.md](./nvidia-forum-gpu-fleet-post.md) | The production GPU fleet: cold weight loads on L4s, min-instances as a quota decision rather than a performance one, the keep-warm cron, and why a failover chain must never have an empty rung |
| [nvidia-forum-browser-digital-human.md](./nvidia-forum-browser-digital-human.md) | Audio2Face-3D streamed onto a rig the visitor generated ninety seconds earlier |
-| [nvidia-forum-model-retirement-post.md](./nvidia-forum-model-retirement-post.md) | Both models our two live posts featured were retired from the hosted NIM catalog within weeks: why a `410 Gone` is invisible to a fallback chain, the `model@dimension` vector tags that made the embedding retirement survivable, and three lifecycle signals we ask NVIDIA for. Written to the approval pattern below; post this one first |
## Member benefits and current disposition
@@ -367,7 +367,7 @@ record does not.
| AI Podcast guest form | Fetched [ai-podcast.nvidia.com](https://ai-podcast.nvidia.com) | Embedded "Submit Guest Ideas" form, fields recorded above |
| NGC publishing prerequisites | Searched the [NGC Software Partner page](https://www.nvidia.com/en-us/gpu-cloud/ngc-software-partners/) | Legal agreement, staging repo, security scan, QA, sign-off |
| ISV program retired | `WebFetch` on `nvidia.com/en-us/programs/isv/` | HTTP 301 to `developer.nvidia.com` |
-| Both forum posts live | `curl -o /dev/null -w '%{http_code}'` | Both 200 |
+| All three forum posts live | `curl -o /dev/null -w '%{http_code}'` | All 200 |
| `/nvidia` never announced on X | Read [announcement-coverage.md](./announcement-coverage.md) inventory | Column empty for `/nvidia`, populated for `/openai` |
| Jensen Huang engagement has no source | `data/timeline.json`, event `2026-07-18-jensen-huang` | `source_url: null`, as are 4 other NVIDIA events |
| GPU fleet shape | `gcloud run services list` across all regions, filtered to accelerator node selectors | 8 workers, 12 deployments, 11 L4 + 1 RTX PRO 6000 |
diff --git a/docs/partners/opportunities.md b/docs/partners/opportunities.md
index d73b357e1..9f7d410f6 100644
--- a/docs/partners/opportunities.md
+++ b/docs/partners/opportunities.md
@@ -137,7 +137,7 @@ own domain, which is the channel with our best track record.
|---|---|---|
| [nvidia-forum-browser-digital-human.md](../nvidia-forum-browser-digital-human.md) | NVIDIA Developer Forums, post 3 | Owner posts |
| [nvidia-forum-gpu-fleet-post.md](../nvidia-forum-gpu-fleet-post.md) | NVIDIA Developer Forums | Owner posts |
-| [nvidia-forum-model-retirement-post.md](../nvidia-forum-model-retirement-post.md) | NVIDIA Developer Forums, NIM > Models | Owner posts |
+| [nvidia-forum-model-retirement-post.md](../nvidia-forum-model-retirement-post.md) | NVIDIA Developer Forums, NIM > Models | [Posted 2026-09-21](https://forums.developer.nvidia.com/t/nvidia-nim-model-retirements-what-a-410-gone-does-to-a-fallback-chain-and-how-we-survive-it-now/383950) |
| [ibm-community-governed-agents-post.md](../ibm-community-governed-agents-post.md) | Our own IBM user group, against a one-per-week allowance | Owner posts |
| [openai-community-3d-studio-post.md](../openai-community-3d-studio-post.md), [openai-community-physical-world-post.md](../openai-community-physical-world-post.md) | OpenAI Developer Community | Owner posts |
diff --git a/docs/publishing-program-2026-09.md b/docs/publishing-program-2026-09.md
index 9fb9524d0..020becd33 100644
--- a/docs/publishing-program-2026-09.md
+++ b/docs/publishing-program-2026-09.md
@@ -32,7 +32,7 @@ Two rules that apply to every entry, because both have burned publishing program
| 9 | dev.to (canonical back to three.ws) | [devto-mcp-fleet-post.md](./devto-mcp-fleet-post.md) | 72 MCP servers, four traps, four rules, and the one change that mattered more than the fleet | ~1,290 words | Owner approval |
| 10 | Google Cloud Community | [google-cloud-community-post.md](./google-cloud-community-post.md) | One container, 115 scheduled jobs, a GPU fleet that sleeps, and three deploy gates each written the day after an outage | ~1,530 words | Owner approval |
| 11 | NVIDIA Developer Forums (already drafted, earlier) | [nvidia-forum-browser-digital-human.md](./nvidia-forum-browser-digital-human.md) | Audio2Face-3D streamed onto a rig the visitor generated ninety seconds ago | existing draft | Owner approval |
-| 12 | NVIDIA Developer Forums (post this one first) | [nvidia-forum-model-retirement-post.md](./nvidia-forum-model-retirement-post.md) | Both models our live posts featured were retired within weeks: why a 410 is invisible to a fallback chain, vector tags that survive an embedder retirement, three lifecycle asks of NVIDIA | ~2,300 words | Owner approval |
+| 12 | NVIDIA Developer Forums | [nvidia-forum-model-retirement-post.md](./nvidia-forum-model-retirement-post.md) | Both models our live posts featured were retired within weeks: why a 410 is invisible to a fallback chain, vector tags that survive an embedder retirement, three lifecycle asks of NVIDIA | ~2,300 words | [Posted 2026-09-21](https://forums.developer.nvidia.com/t/nvidia-nim-model-retirements-what-a-410-gone-does-to-a-fallback-chain-and-how-we-survive-it-now/383950) |
## Short-form entries