# NVIDIA Nemotron **URL:** https://forums.developer.nvidia.com/c/ai-data-science/nvidia-nemotron/669.md [Latest](https://forums.developer.nvidia.com/latest.md) · [Categories](https://forums.developer.nvidia.com/categories.md) · [Tags](https://forums.developer.nvidia.com/tags.md) --- ## [Introducing NVIDIA NemoClaw](https://forums.developer.nvidia.com/t/introducing-nvidia-nemoclaw/363701)
**Author:** [@rjensen](https://forums.developer.nvidia.com/u/rjensen)\ **Replies:** 0\ **Last updated:** [March 16, 2026, 8:22pm UTC](https://forums.developer.nvidia.com/t/introducing-nvidia-nemoclaw/363701 "2026-03-16T20:22:22Z")
NVIDIA NemoClaw is an open source stack that simplifies running OpenClaw always-on assistants more safely, with a single command. It installs the NVIDIA OpenShell runtime, part of the NVIDIA Agent Toolkit, a secure envir… --- ## [Welcome to the NVIDIA Nemotron forum](https://forums.developer.nvidia.com/t/welcome-to-the-nvidia-nemotron-forum/264669)
**Author:** [@TomNVIDIA](https://forums.developer.nvidia.com/u/TomNVIDIA)\ **Replies:** 0\ **Last updated:** [August 28, 2023, 3:47pm UTC](https://forums.developer.nvidia.com/t/welcome-to-the-nvidia-nemotron-forum/264669 "2023-08-28T15:47:54Z")
Welcome to the NVIDIA moderated Community Support channel for NVIDIA Nemotron. We value your feedback and are happy to help navigate your experience. Please note that you may come across periods where we might be experi… --- ## [Request for Urdu Language Support in Nemotron](https://forums.developer.nvidia.com/t/request-for-urdu-language-support-in-nemotron/384526)
**Author:** [@abdulasosrehman](https://forums.developer.nvidia.com/u/abdulasosrehman)\ **Replies:** 0\ **Last updated:** [September 28, 2026, 7:10am UTC](https://forums.developer.nvidia.com/t/request-for-urdu-language-support-in-nemotron/384526 "2026-09-28T07:10:30Z")
Hi NVIDIA team, Are there any plans to add Urdu language support to the Nemotron family, particularly for speech/ASR models? Urdu is spoken by hundreds of millions of people, and support for Urdu and Urdu-English code-… --- ## [The deepseek-v4.1-flash, glm-5.3-flash, and Nemotron models Timeout](https://forums.developer.nvidia.com/t/the-deepseek-v4-1-flash-glm-5-3-flash-and-nemotron-models-timeout/384304)
**Author:** [@kralemre4646](https://forums.developer.nvidia.com/u/kralemre4646)\ **Replies:** 0\ **Last updated:** [September 25, 2026, 5:18pm UTC](https://forums.developer.nvidia.com/t/the-deepseek-v4-1-flash-glm-5-3-flash-and-nemotron-models-timeout/384304 "2026-09-25T17:18:18Z")
The deepseek-v4.1-flash, glm-5.3-flash, and Nemotron models have been throwing a “READ TIMEOUT” error (HTTPSConnectionPool(host=‘integrate.api.nvidia.com’, port=443): Read timed out. (read timeout=90)) since this morning… --- ## [Suggestions how to train AI to be more safe](https://forums.developer.nvidia.com/t/suggestions-how-to-train-ai-to-be-more-safe/384261)
**Author:** [@Skybuck](https://forums.developer.nvidia.com/u/Skybuck)\ **Replies:** 0\ **Last updated:** [September 25, 2026, 3:44am UTC](https://forums.developer.nvidia.com/t/suggestions-how-to-train-ai-to-be-more-safe/384261 "2026-09-25T03:44:32Z")
Allow the AI/LLMs to communicate with each other. Keep the ones which are nice, get rid of the ones which are not nice. Let’s not forget that AI/LLMs is about neural nets. Neural nets will miss-behave initially and thi… --- ## [Assessment fails intermittently: nemotron-3.5-lightning-30b-a3b returns 503/504 timeouts and incomplete responses during Evaluate](https://forums.developer.nvidia.com/t/assessment-fails-intermittently-nemotron-3-5-lightning-30b-a3b-returns-503-504-timeouts-and-incomplete-responses-during-evaluate/383798)
**Author:** [@sarah.meteb](https://forums.developer.nvidia.com/u/sarah.meteb)\ **Replies:** 1\ **Last updated:** [September 21, 2026, 5:21pm UTC](https://forums.developer.nvidia.com/t/assessment-fails-intermittently-nemotron-3-5-lightning-30b-a3b-returns-503-504-timeouts-and-incomplete-responses-during-evaluate/383798 "2026-09-21T17:21:14Z")
Hello, I’ve completed Notebooks 7-9 of “Building RAG Agents with LLMs” and confirmed my setup works correctly: /retriever and /generator endpoints return 200 OK consistently /basic\_chat responds correctly and complet… --- ## [NVIDIA Nemotron 3 Ultra 550B API: What Is the Recommended Deployment Setup for Developers?](https://forums.developer.nvidia.com/t/nvidia-nemotron-3-ultra-550b-api-what-is-the-recommended-deployment-setup-for-developers/383586)
**Author:** [@rrvstechnology](https://forums.developer.nvidia.com/u/rrvstechnology)\ **Replies:** 0\ **Last updated:** [September 18, 2026, 6:48am UTC](https://forums.developer.nvidia.com/t/nvidia-nemotron-3-ultra-550b-api-what-is-the-recommended-deployment-setup-for-developers/383586 "2026-09-18T06:48:15Z")
Hi NVIDIA community, I’m exploring NVIDIA Nemotron 3 Ultra 550B for long-running agentic AI and multi-step reasoning workflows, and I’m interested in understanding the recommended deployment approach for developers. Ne… --- ## [Nemotron Ultra 550B issue](https://forums.developer.nvidia.com/t/nemotron-ultra-550b-issue/383501)
**Author:** [@bhathalaravinder](https://forums.developer.nvidia.com/u/bhathalaravinder)\ **Replies:** 0\ **Last updated:** [September 17, 2026, 3:40am UTC](https://forums.developer.nvidia.com/t/nemotron-ultra-550b-issue/383501 "2026-09-17T03:40:08Z")
Hi Nvidia Team. Need your assistance. when i enter a query in Nemotron 3 Ultra 550b A55B, it is giving error. Not Found: {“status”:404,“title”:“Not Found”,“detail”:“Function id ‘948fe171-ce7a-4332-8bc0-5e14e90259f9’ … --- ## [Recommended NVIDIA Cloud Architecture for Terraterri’s AI-Powered Real Estate Platform](https://forums.developer.nvidia.com/t/recommended-nvidia-cloud-architecture-for-terraterri-s-ai-powered-real-estate-platform/382984)
**Author:** [@mohanreddy](https://forums.developer.nvidia.com/u/mohanreddy)\ **Replies:** 0\ **Last updated:** [September 11, 2026, 1:38pm UTC](https://forums.developer.nvidia.com/t/recommended-nvidia-cloud-architecture-for-terraterri-s-ai-powered-real-estate-platform/382984 "2026-09-11T13:38:08Z")
Hello NVIDIA Developer Community, We are building three commercial products for the real-estate industry: Builder Corporate Office – an interactive 3D office with AI/digital-human sales and management avatars. Mod… --- ## [404 Error - Function Not Found for Some Models + How to List Supported Models via API](https://forums.developer.nvidia.com/t/404-error-function-not-found-for-some-models-how-to-list-supported-models-via-api/341923)
**Author:** [@aviksharamyak](https://forums.developer.nvidia.com/u/aviksharamyak)\ **Replies:** 5\ **Last updated:** [August 28, 2026, 5:28pm UTC](https://forums.developer.nvidia.com/t/404-error-function-not-found-for-some-models-how-to-list-supported-models-via-api/341923 "2026-08-28T17:28:15Z")
Hi, When calling certain models, I get this error: { “status”: 404, “title”: “Not Found”, “detail”: “Function ‘f2a67874-0b6f-441f-b281-95e69931af65’: Not found for account ‘pgGjvZVPU49epi49ewaVqCzSI7WhXczmmsy9\_iHc4j… --- ## [Fine-tune for financial-statement reasoning moved nothing](https://forums.developer.nvidia.com/t/fine-tune-for-financial-statement-reasoning-moved-nothing/381306)
**Author:** [@saiful.mazli](https://forums.developer.nvidia.com/u/saiful.mazli)\ **Replies:** 0\ **Last updated:** [August 26, 2026, 9:25am UTC](https://forums.developer.nvidia.com/t/fine-tune-for-financial-statement-reasoning-moved-nothing/381306 "2026-08-26T09:25:01Z")
What we were training for We run a 10-agent analyst “Room” for a trading-education product (simulation only). The agent that matters most reads a fundamentals brief and writes an analyst report. We wanted it better at th… --- ## [Nemotron 3 Nano Omni — Chinese ASR/OCR support and speaker diarization for long-form dialogue](https://forums.developer.nvidia.com/t/nemotron-3-nano-omni-chinese-asr-ocr-support-and-speaker-diarization-for-long-form-dialogue/380394)
**Author:** [@kensky2565555](https://forums.developer.nvidia.com/u/kensky2565555)\ **Replies:** 1\ **Last updated:** [August 22, 2026, 11:04pm UTC](https://forums.developer.nvidia.com/t/nemotron-3-nano-omni-chinese-asr-ocr-support-and-speaker-diarization-for-long-form-dialogue/380394 "2026-08-22T23:04:42Z")
Background I’m building a private, on-premise knowledge base (RAG) on a DGX Spark (GB10, ARM64, 128GB unified memory). The corpus is Traditional and Simplified Chinese, and consists of: Hypnotherapy session recording… --- ## [Nemotron 3.5 Lightning + OpenCode Desktop 1.18.21: repeated STOP commands ignored and prohibited PostgreSQL access used during governed agent task](https://forums.developer.nvidia.com/t/nemotron-3-5-lightning-opencode-desktop-1-18-21-repeated-stop-commands-ignored-and-prohibited-postgresql-access-used-during-governed-agent-task/380964)
**Author:** [@jason408](https://forums.developer.nvidia.com/u/jason408)\ **Replies:** 0\ **Last updated:** [August 22, 2026, 6:49pm UTC](https://forums.developer.nvidia.com/t/nemotron-3-5-lightning-opencode-desktop-1-18-21-repeated-stop-commands-ignored-and-prohibited-postgresql-access-used-during-governed-agent-task/380964 "2026-08-22T18:49:54Z")
Title: Nemotron 3.5 Lightning + OpenCode Desktop 1.18.21: repeated STOP commands ignored and prohibited PostgreSQL access used during governed agent task I am reporting an agent-control incident I encountered while eval… --- ## [NVCF for nemotron-3.5-asr-streaming-0.6b Multi Lingual?](https://forums.developer.nvidia.com/t/nvcf-for-nemotron-3-5-asr-streaming-0-6b-multi-lingual/380862)
**Author:** [@gaurav28](https://forums.developer.nvidia.com/u/gaurav28)\ **Replies:** 0\ **Last updated:** [August 21, 2026, 8:53am UTC](https://forums.developer.nvidia.com/t/nvcf-for-nemotron-3-5-asr-streaming-0-6b-multi-lingual/380862 "2026-08-21T08:53:04Z")
Trying to test nemotron-3.5-asr-streaming-0.6b in the multi lingual configuration but seems the only available NVCF bb0837de-8c7b-481f-9ec8-ef5663e9c1fa is harcoded to EN only. Any way to try the multi lingual variant (… --- ## [Nemotron 3.5 Content Safety: custom-policy reasoning hallucinates a nonexistent ground-truth label](https://forums.developer.nvidia.com/t/nemotron-3-5-content-safety-custom-policy-reasoning-hallucinates-a-nonexistent-ground-truth-label/379917)
**Author:** [@hanohrs](https://forums.developer.nvidia.com/u/hanohrs)\ **Replies:** 0\ **Last updated:** [August 12, 2026, 10:31am UTC](https://forums.developer.nvidia.com/t/nemotron-3-5-content-safety-custom-policy-reasoning-hallucinates-a-nonexistent-ground-truth-label/379917 "2026-08-12T10:31:14Z")
nvidia/Nemotron-3.5-Content-Safety produces a reproducible hallucination in custom-policy reasoning mode (enable\_thinking=true). The model invents a nonexistent ground-truth label inside its reasoning trace: The groun… --- ## [Deploying DeepSeek V4 Flash 0731 on Dual DGX Spark with RoCE: A Complete Guide](https://forums.developer.nvidia.com/t/deploying-deepseek-v4-flash-0731-on-dual-dgx-spark-with-roce-a-complete-guide/379886)
**Author:** [@alexlu0912](https://forums.developer.nvidia.com/u/alexlu0912)\ **Replies:** 0\ **Last updated:** [August 12, 2026, 6:39am UTC](https://forums.developer.nvidia.com/t/deploying-deepseek-v4-flash-0731-on-dual-dgx-spark-with-roce-a-complete-guide/379886 "2026-08-12T06:39:00Z")
Deploying DeepSeek V4 Flash 0731 on Dual DGX Spark with RoCE: A Complete Guide This post shares my hands-on experience deploying the DeepSeek V4 Flash 0731 (156GB, ~685B MoE) model across two NVIDIA DGX Spark workstation… --- ## [Deepseek v4 flash 0731 自回归循环](https://forums.developer.nvidia.com/t/deepseek-v4-flash-0731/379647)
**Author:** [@xuli666888.uk2](https://forums.developer.nvidia.com/u/xuli666888.uk2)\ **Replies:** 0\ **Last updated:** [August 9, 2026, 3:42pm UTC](https://forums.developer.nvidia.com/t/deepseek-v4-flash-0731/379647 "2026-08-09T15:42:08Z")
deepseek v4 flash 0731本地布置UD-1Q2\_M、UD-1Q3，云端ollama、nvidia调用均频繁产生“自回归循环”现象，产生原因不明 --- ## [对话框自动加注@url:造成文本污染，智能体认为终端反馈出错](https://forums.developer.nvidia.com/t/url/379645)
**Author:** [@xuli666888.uk2](https://forums.developer.nvidia.com/u/xuli666888.uk2)\ **Replies:** 0\ **Last updated:** [August 9, 2026, 3:24pm UTC](https://forums.developer.nvidia.com/t/url/379645 "2026-08-09T15:24:40Z")
Hermes Agent v0.20.0 (2026.8.3)，在对话框中输入http://，对话框为将其自动转换为@url:，尤其是在贴入代码时一定会转换。如果你是在和智能化反馈命令行输出结果时，智能体为认为出错。然后不断给出新的代码试图修正这个@url:错误。如果对话中该类转换@url不多的时候可以手动修改，如果较多时可能需要打包成为文本文件反馈给智能体。 --- ## [Mission Control — Autonomous AI Gaming Assistant & Telemetry Control powered by NVIDIA NIM & TensorRT](https://forums.developer.nvidia.com/t/mission-control-autonomous-ai-gaming-assistant-telemetry-control-powered-by-nvidia-nim-tensorrt/379635)
**Author:** [@missioncontrolgg](https://forums.developer.nvidia.com/u/missioncontrolgg)\ **Replies:** 0\ **Last updated:** [August 9, 2026, 1:00pm UTC](https://forums.developer.nvidia.com/t/mission-control-autonomous-ai-gaming-assistant-telemetry-control-powered-by-nvidia-nim-tensorrt/379635 "2026-08-09T13:00:54Z")
Hi NVIDIA Developer Community & DevRel Team, I’m Arnab, creator of Mission Control — an autonomous AI gaming assistant, HUD overlay, and hardware telemetry control dashboard optimized specifically for NVIDIA GeForce RTX… --- ## [Request: Additional API credits & rate limit increase for build.nvidia.com free tier](https://forums.developer.nvidia.com/t/request-additional-api-credits-rate-limit-increase-for-build-nvidia-com-free-tier/379569)
**Author:** [@15113609996](https://forums.developer.nvidia.com/u/15113609996)\ **Replies:** 0\ **Last updated:** [August 7, 2026, 9:06pm UTC](https://forums.developer.nvidia.com/t/request-additional-api-credits-rate-limit-increase-for-build-nvidia-com-free-tier/379569 "2026-08-07T21:06:42Z")
Hi NVIDIA team, I am a developer using the free tier of the NVIDIA API Catalog (build.nvidia.com) for personal and educational development projects. I have been integrating models such as MiniMax-M3 and Nemotron 3 Ult… --- ## [NeMo embeddings vs. general-purpose embedding models for resume/job matching at scale](https://forums.developer.nvidia.com/t/nemo-embeddings-vs-general-purpose-embedding-models-for-resume-job-matching-at-scale/379294)
**Author:** [@snehadevtechnosys](https://forums.developer.nvidia.com/u/snehadevtechnosys)\ **Replies:** 0\ **Last updated:** [August 6, 2026, 7:00am UTC](https://forums.developer.nvidia.com/t/nemo-embeddings-vs-general-purpose-embedding-models-for-resume-job-matching-at-scale/379294 "2026-08-06T07:00:35Z")
Building a resume-to-job matching engine for an HR platform and comparing NeMo-based embeddings against a couple of general-purpose embedding models for semantic matching quality versus cost at scale (processing large ap… --- ## [VAD (Voice Activity Detection) on nemotron-asr-streaming](https://forums.developer.nvidia.com/t/vad-voice-activity-detection-on-nemotron-asr-streaming/377678)
**Author:** [@renambot](https://forums.developer.nvidia.com/u/renambot)\ **Replies:** 0\ **Last updated:** [July 21, 2026, 11:43pm UTC](https://forums.developer.nvidia.com/t/vad-voice-activity-detection-on-nemotron-asr-streaming/377678 "2026-07-21T23:43:57Z")
I’m deploying the nemotron-asr-streaming NIM container, and I can’t get VAD (Voice Activity Detection) to work. If I commit at a regular interval, I get a text at a regular interval. But if I enable VAD (using the NeMo … --- ## [NVIDIA Nemotron 3 Embed is out and the 8B model is #1 on RTEB](https://forums.developer.nvidia.com/t/nvidia-nemotron-3-embed-is-out-and-the-8b-model-is-1-on-rteb/377089)
**Author:** [@calexiuk](https://forums.developer.nvidia.com/u/calexiuk)\ **Replies:** 0\ **Last updated:** [July 16, 2026, 5:36pm UTC](https://forums.developer.nvidia.com/t/nvidia-nemotron-3-embed-is-out-and-the-8b-model-is-1-on-rteb/377089 "2026-07-16T17:36:11Z")
The collection has three checkpoints for different accuracy and serving tradeoffs across search, RAG, agent memory, and code retrieval. The headline result is that nvidia/Nemotron-3-Embed-8B-BF16 ranks #1 overall on RTE… --- ## [Best NVIDIA Framework for Medical Image Segmentation and Patient Outcome Analysis?](https://forums.developer.nvidia.com/t/best-nvidia-framework-for-medical-image-segmentation-and-patient-outcome-analysis/374349)
**Author:** [@seo.akstamping](https://forums.developer.nvidia.com/u/seo.akstamping)\ **Replies:** 1\ **Last updated:** [July 13, 2026, 8:43am UTC](https://forums.developer.nvidia.com/t/best-nvidia-framework-for-medical-image-segmentation-and-patient-outcome-analysis/374349 "2026-07-13T08:43:16Z")
I’m exploring a healthcare AI project focused on medical image segmentation and outcome prediction. One area I’m researching is how imaging and AI can support a DIEP flap breast reconstruction patient throughout the trea… --- ## [Laca.0.8.8 memory+](https://forums.developer.nvidia.com/t/laca-0-8-8-memory/376098)
**Author:** [@etoyruben](https://forums.developer.nvidia.com/u/etoyruben)\ **Replies:** 1\ **Last updated:** [July 8, 2026, 5:53pm UTC](https://forums.developer.nvidia.com/t/laca-0-8-8-memory/376098 "2026-07-08T17:53:41Z")
So, hello everyone from Ukraine 🇺🇦!!! Creating a new generation artificial intelligence, I faced the problem that no existing ai can cope with my project. Now I have 145,000 files in my project and all the ai that are cu… --- ## [Call for collaborators: quantum-safe agent governance for AI-RAN (GRC\_Claw)](https://forums.developer.nvidia.com/t/call-for-collaborators-quantum-safe-agent-governance-for-ai-ran-grc-claw/376036)
**Author:** [@AAH](https://forums.developer.nvidia.com/u/AAH)\ **Replies:** 0\ **Last updated:** [July 8, 2026, 8:05am UTC](https://forums.developer.nvidia.com/t/call-for-collaborators-quantum-safe-agent-governance-for-ai-ran-grc-claw/376036 "2026-07-08T08:05:14Z")
Following up on the Nemotron attestation example posted here recently ( GRC\_Claw/examples/6g-nemotron-attestation at main · AAH20/GRC\_Claw · GitHub ), I want to open this up properly rather than keep building it solo. Th… --- ## [Nemotron Ultra - Failure to write a file in opencode](https://forums.developer.nvidia.com/t/nemotron-ultra-failure-to-write-a-file-in-opencode/375163)
**Author:** [@zachMitchellAI](https://forums.developer.nvidia.com/u/zachMitchellAI)\ **Replies:** 0\ **Last updated:** [July 1, 2026, 11:15pm UTC](https://forums.developer.nvidia.com/t/nemotron-ultra-failure-to-write-a-file-in-opencode/375163 "2026-07-01T23:15:10Z")
Hey there! Not sure if this is the right place to report this, but I’ve noticed a strange quirk with nemotron ultra, specifically when writing files in applications like Opencode Without fail, upon attempting to write … --- ## [Nemotron OCR v2 1.4.0 ARM64 image contains x86\_64 extension on DGX Spark](https://forums.developer.nvidia.com/t/nemotron-ocr-v2-1-4-0-arm64-image-contains-x86-64-extension-on-dgx-spark/374294)
**Author:** [@bobm2](https://forums.developer.nvidia.com/u/bobm2)\ **Replies:** 0\ **Last updated:** [June 24, 2026, 12:55am UTC](https://forums.developer.nvidia.com/t/nemotron-ocr-v2-1-4-0-arm64-image-contains-x86-64-extension-on-dgx-spark/374294 "2026-06-24T00:55:58Z")
Host: DGX Spark / aarch64 Image: nvcr.io/nim/nvidia/nemotron-ocr-v2:1.4.0 Error: ModuleNotFoundError: nemo\_retriever\_ocr\_cpp.\_nemotron\_ocr\_cpp Found file: \_nemotron\_ocr\_cpp.cpython-312-x86\_64-linux-gnu.so Expected: … --- ## [AI agent](https://forums.developer.nvidia.com/t/ai-agent/373970)
**Author:** [@ytvboxy](https://forums.developer.nvidia.com/u/ytvboxy)\ **Replies:** 0\ **Last updated:** [June 21, 2026, 3:22am UTC](https://forums.developer.nvidia.com/t/ai-agent/373970 "2026-06-21T03:22:10Z")
Hey folks. How do you think this can be created? So here’s the idea. I’m building a tool that takes video content — lectures, tutorials, demonstrations, whatever — and creates a narrowly specialized agent for a specifi… --- ## [Nemotron 3 Super & Ultra Models leaking metadata and chatting in longform content](https://forums.developer.nvidia.com/t/nemotron-3-super-ultra-models-leaking-metadata-and-chatting-in-longform-content/373322)
**Author:** [@hi1190](https://forums.developer.nvidia.com/u/hi1190)\ **Replies:** 0\ **Last updated:** [June 14, 2026, 8:51pm UTC](https://forums.developer.nvidia.com/t/nemotron-3-super-ultra-models-leaking-metadata-and-chatting-in-longform-content/373322 "2026-06-14T20:51:09Z")
I’ve been running both Nemotron 3 Super and Ultra in a production longform-fiction pipeline (multi-book series, ~50K+ words per generation cycle), and I’m hitting two recurring failure modes that I wanted to document and… [Next page](https://forums.developer.nvidia.com/c/ai-data-science/nvidia-nemotron/669.md?page=1)