# \#dgx-station **URL:** https://forums.developer.nvidia.com/tag/dgx-station/1183.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) --- ## [DeepSeek-V4-Flash on 2x DGX Spark throughput collapses at large prompt+concurrency. Would a 4x stack + Vision-Exp fix it?](https://forums.developer.nvidia.com/t/deepseek-v4-flash-on-2x-dgx-spark-throughput-collapses-at-large-prompt-concurrency-would-a-4x-stack-vision-exp-fix-it/384069)
**Author:** [@ammarabbaxi13](https://forums.developer.nvidia.com/u/ammarabbaxi13)\ **Replies:** 0\ **Last updated:** [September 23, 2026, 7:49am UTC](https://forums.developer.nvidia.com/t/deepseek-v4-flash-on-2x-dgx-spark-throughput-collapses-at-large-prompt-concurrency-would-a-4x-stack-vision-exp-fix-it/384069 "2026-09-23T07:49:48Z")
Hi all, I’m running DeepSeek-V4-Flash-Vision-exp across 2x DGX Spark (TP=2) using the MIAI Labs Recipe. Our target is ≥500K context with 8 concurrent users, but I’m noticing token generation speed and TTFT dropping sha… --- ## [Can the ConnectX-8 in DGX Station operate in InfiniBand mode and connect to a Q3200 InfiniBand switch?](https://forums.developer.nvidia.com/t/can-the-connectx-8-in-dgx-station-operate-in-infiniband-mode-and-connect-to-a-q3200-infiniband-switch/383408)
**Author:** [@enhar](https://forums.developer.nvidia.com/u/enhar)\ **Replies:** 1\ **Last updated:** [September 16, 2026, 10:30am UTC](https://forums.developer.nvidia.com/t/can-the-connectx-8-in-dgx-station-operate-in-infiniband-mode-and-connect-to-a-q3200-infiniband-switch/383408 "2026-09-16T10:30:24Z")
Can the ConnectX-8 in DGX Station operate in InfiniBand mode and connect to a Q3200 InfiniBand switch? Hello, I would like to clarify the networking capabilities of the ConnectX-8 SuperNIC integrated into NVIDIA DGX Sta… --- ## [Pushing GB10 to the Limit: Qwen3 235B MoE + Concurrent Best-of-4 + Persistent Agent Layer. Architecture check & Optimization tips?](https://forums.developer.nvidia.com/t/pushing-gb10-to-the-limit-qwen3-235b-moe-concurrent-best-of-4-persistent-agent-layer-architecture-check-optimization-tips/373118)
**Author:** [@ludbzh](https://forums.developer.nvidia.com/u/ludbzh)\ **Replies:** 0\ **Last updated:** [June 12, 2026, 7:21am UTC](https://forums.developer.nvidia.com/t/pushing-gb10-to-the-limit-qwen3-235b-moe-concurrent-best-of-4-persistent-agent-layer-architecture-check-optimization-tips/373118 "2026-06-12T07:21:15Z")
Hey everyone, I’m architecting a high-performance local AI node around a single ASUS Ascent GX10 (NVIDIA GB10 Grace Blackwell, SM121, 128GB unified LPDDR5x). The goal is to maximize reasoning depth and throughput on a s… --- ## [DGX DL WS 4V100 upgrade BIOS OS 4](https://forums.developer.nvidia.com/t/dgx-dl-ws-4v100-upgrade-bios-os-4/372725)
**Author:** [@Freedom12345](https://forums.developer.nvidia.com/u/Freedom12345)\ **Replies:** 0\ **Last updated:** [June 9, 2026, 3:56pm UTC](https://forums.developer.nvidia.com/t/dgx-dl-ws-4v100-upgrade-bios-os-4/372725 "2026-06-09T15:56:18Z")
Hello everyone, I have a DGX WS 4V100 workstation running OS 4. I wanted to upgrade to the latest version of OS 4, so I first updated the BIOS from the ASUS website. Now, I have no video output from the first V100 card … --- ## [DGX Station V100 stuck on "press DEL or F2" Boot Screen](https://forums.developer.nvidia.com/t/dgx-station-v100-stuck-on-press-del-or-f2-boot-screen/359572)
**Author:** [@aschlieb](https://forums.developer.nvidia.com/u/aschlieb)\ **Replies:** 2\ **Last updated:** [February 24, 2026, 3:50pm UTC](https://forums.developer.nvidia.com/t/dgx-station-v100-stuck-on-press-del-or-f2-boot-screen/359572 "2026-02-24T15:50:38Z")
Hi, I was planning to perform a clean install of DGX OS 6.3.2 on our V100 system. After fully wiping the four SSDs in the JBOD, I tried booting into the BIOS to select my bootable USB drive for installation. For some re… --- ## [DGX OS 7 Reimage ISO for DGX Spark (HP ZGX Nano G1n)](https://forums.developer.nvidia.com/t/dgx-os-7-reimage-iso-for-dgx-spark-hp-zgx-nano-g1n/357413)
**Author:** [@sai-sysengineer](https://forums.developer.nvidia.com/u/sai-sysengineer)\ **Replies:** 8\ **Last updated:** [January 16, 2026, 4:04am UTC](https://forums.developer.nvidia.com/t/dgx-os-7-reimage-iso-for-dgx-spark-hp-zgx-nano-g1n/357413 "2026-01-16T04:04:47Z")
Hello, I’m looking for guidance on obtaining the official DGX OS 7 reimage ISO for the DGX Spark platform. It took me a few hours to get to talk to someone on the HP side which apparently, they said they would provide … --- ## [DGX Spark Playbooks: Agentic RAG: Chat UI errors out](https://forums.developer.nvidia.com/t/dgx-spark-playbooks-agentic-rag-chat-ui-errors-out/357223)
**Author:** [@ms6174](https://forums.developer.nvidia.com/u/ms6174)\ **Replies:** 3\ **Last updated:** [January 13, 2026, 5:44pm UTC](https://forums.developer.nvidia.com/t/dgx-spark-playbooks-agentic-rag-chat-ui-errors-out/357223 "2026-01-13T17:44:26Z")
Hi, I’m trying out the “RAG Application in AI Workbench“ RAG chat UI playbook. I could start the container and view the GUI: However, when I send a user input, I get the following 403 error: File “/home/workbench/…