# Product Q&A **URL:** https://forum.verda.com/c/product-q-a/6.md [Latest](https://forum.verda.com/latest.md) · [Categories](https://forum.verda.com/categories.md) · [Tags](https://forum.verda.com/tags.md) --- ## [Product Q&A Guidelines](https://forum.verda.com/t/product-q-a-guidelines/28)
**Author:** [@TeamVerda](https://forum.verda.com/u/TeamVerda)\ **Replies:** 0\ **Last updated:** [August 13, 2025, 6:21am UTC](https://forum.verda.com/t/product-q-a-guidelines/28 "2025-08-13T06:21:39Z")
1. Search Before Posting Use the search bar to see if your question has already been answered Check the Product Documentation or FAQ first — many common questions are covered there 2. How to Ask a Good Question W… --- ## [Single-B300 Validation of Llama 3.3 70B + Runtime LoRA: SDPA Recovery, Telemetry and Next Benchmark Design](https://forum.verda.com/t/single-b300-validation-of-llama-3-3-70b-runtime-lora-sdpa-recovery-telemetry-and-next-benchmark-design/87)
**Author:** [@HumAI](https://forum.verda.com/u/HumAI)\ **Replies:** 0\ **Last updated:** [July 3, 2026, 9:09pm UTC](https://forum.verda.com/t/single-b300-validation-of-llama-3-3-70b-runtime-lora-sdpa-recovery-telemetry-and-next-benchmark-design/87 "2026-07-03T21:09:45Z")
Single-B300 Validation of Llama 3.3 70B + Runtime LoRA Hello Verda community, I am Edin Vučelj from BPM RED Academy in Bosnia and Herzegovina. We recently completed a controlled, application-level validation… --- ## [B300 Spot Uptime](https://forum.verda.com/t/b300-spot-uptime/85)
**Author:** [@alpha\_ai](https://forum.verda.com/u/alpha_ai)\ **Replies:** 3\ **Last updated:** [May 7, 2026, 8:37am UTC](https://forum.verda.com/t/b300-spot-uptime/85 "2026-05-07T08:37:49Z")
Hi, We are interested in a 4x B300 instance (4B300.120V), and we would like to know what average uptimes we could expect for the spot instances. Do you have any metrics on average uptime for the past 30 days, or just a… --- ## [Hibernated instance lists?](https://forum.verda.com/t/hibernated-instance-lists/83)
**Author:** [@Alpaca](https://forum.verda.com/u/Alpaca)\ **Replies:** 1\ **Last updated:** [March 9, 2026, 1:35pm UTC](https://forum.verda.com/t/hibernated-instance-lists/83 "2026-03-09T13:35:46Z")
how can I check hibernated instance lists? --- ## [RTX PRO 6000 Test?](https://forum.verda.com/t/rtx-pro-6000-test/80)
**Author:** [@echovibexD](https://forum.verda.com/u/echovibexD)\ **Replies:** 1\ **Last updated:** [January 28, 2026, 3:49pm UTC](https://forum.verda.com/t/rtx-pro-6000-test/80 "2026-01-28T15:49:20Z")
Has anyone tried it? Is it that big of a difference compared to the 5090? Curious to try it out. Vera pricing seems much better than Runpod’s --- ## [Scale-down Delay Configuration Request](https://forum.verda.com/t/scale-down-delay-configuration-request/77)
**Author:** [@pixelrune](https://forum.verda.com/u/pixelrune)\ **Replies:** 1\ **Last updated:** [December 18, 2025, 3:49pm UTC](https://forum.verda.com/t/scale-down-delay-configuration-request/77 "2025-12-18T15:49:23Z")
hi,I’m running an image generation deployment on verda serverless containers and would like to increase the scale-down delay from the default 300s to 1800s. My cold start time is around 80-90s, which significantly impac… --- ## [Shared storage for Serverless Containers](https://forum.verda.com/t/shared-storage-for-serverless-containers/63)
**Author:** [@ElGrandeAmericano](https://forum.verda.com/u/ElGrandeAmericano)\ **Replies:** 1\ **Last updated:** [October 6, 2025, 8:58am UTC](https://forum.verda.com/t/shared-storage-for-serverless-containers/63 "2025-10-06T08:58:20Z")
Hi team, I’d like to ask for shared storage for serverless containers. It’s telling me to add /data storage 500GB, but when I deploy the container, I don’t see any shared storage in the shared filesystems tab. How can … --- ## [Iommu bindings inside an instance or a container](https://forum.verda.com/t/iommu-bindings-inside-an-instance-or-a-container/58)
**Author:** [@pixelrune](https://forum.verda.com/u/pixelrune)\ **Replies:** 3\ **Last updated:** [September 25, 2025, 2:12pm UTC](https://forum.verda.com/t/iommu-bindings-inside-an-instance-or-a-container/58 "2025-09-25T14:12:20Z")
Hey is it possible for iommu bindings to be accessible inside an instance or a container? Or is it possible to upload a custom os to be used by an instance? --- ## [Lost HDD due to computer crashing](https://forum.verda.com/t/lost-hdd-due-to-computer-crashing/51)
**Author:** [@echovibexD](https://forum.verda.com/u/echovibexD)\ **Replies:** 1\ **Last updated:** [September 15, 2025, 9:02am UTC](https://forum.verda.com/t/lost-hdd-due-to-computer-crashing/51 "2025-09-15T09:02:25Z")
Hi, my computer just crashed out of nowhere and I lost the HDD completely which had my private keys for logging into the instances. Is it possible to get back on those instances? Is there a web SSH that I could do or cou… --- ## [B200 availability](https://forum.verda.com/t/b200-availability/50)
**Author:** [@pixelrune](https://forum.verda.com/u/pixelrune)\ **Replies:** 1\ **Last updated:** [September 15, 2025, 7:50am UTC](https://forum.verda.com/t/b200-availability/50 "2025-09-15T07:50:32Z")
just curiosity but what’s the availability for 8xB200 spot? I notice that none are currently available. Are they usually like this? Also, do you have any stats on how often they are interrupted? --- ## [B200 for model training](https://forum.verda.com/t/b200-for-model-training/35)
**Author:** [@Sky\_drifty](https://forum.verda.com/u/Sky_drifty)\ **Replies:** 5\ **Last updated:** [September 4, 2025, 11:30am UTC](https://forum.verda.com/t/b200-for-model-training/35 "2025-09-04T11:30:47Z")
I need 2x of x8-B200 instances for a model training (connected with infiniband). How can I do that? --- ## [Run Ollama on the cloud server](https://forum.verda.com/t/run-ollama-on-the-cloud-server/39)
**Author:** [@Sky\_drifty](https://forum.verda.com/u/Sky_drifty)\ **Replies:** 1\ **Last updated:** [September 2, 2025, 12:57pm UTC](https://forum.verda.com/t/run-ollama-on-the-cloud-server/39 "2025-09-02T12:57:27Z")
How can I run ollama using serverless container on DataCrunch’s cloud server? --- ## [Increasing model download speeds from Hugging Face](https://forum.verda.com/t/increasing-model-download-speeds-from-hugging-face/40)
**Author:** [@Alpaca](https://forum.verda.com/u/Alpaca)\ **Replies:** 1\ **Last updated:** [September 3, 2025, 10:16am UTC](https://forum.verda.com/t/increasing-model-download-speeds-from-hugging-face/40 "2025-09-03T10:16:19Z")
Hi, What optimizations would you recommend for increasing model download speeds from Hugging Face? --- ## [Limit in containers API](https://forum.verda.com/t/limit-in-containers-api/32)
**Author:** [@Alpaca](https://forum.verda.com/u/Alpaca)\ **Replies:** 1\ **Last updated:** [August 26, 2025, 7:18am UTC](https://forum.verda.com/t/limit-in-containers-api/32 "2025-08-26T07:18:00Z")
Hi, A quick question: Is there a fixed upload limit by DataCrunch in containers API?